KJ Trading Systems Kevin Davey - Ask Me Anything (AMA) - futures io
futures io futures trading



KJ Trading Systems Kevin Davey - Ask Me Anything (AMA)


Discussion in Trading Reviews and Vendors

Updated
      Top Posters
    1. looks_one kevinkdog with 180 posts (416 thanks)
    2. looks_two SMCJB with 23 posts (40 thanks)
    3. looks_3 Mabi with 17 posts (12 thanks)
    4. looks_4 bluefightingcat with 16 posts (9 thanks)
      Best Posters
    1. looks_one grausch with 2.8 thanks per post
    2. looks_two kevinkdog with 2.3 thanks per post
    3. looks_3 SMCJB with 1.7 thanks per post
    4. looks_4 Big Mike with 1.5 thanks per post
    1. trending_up 106,636 views
    2. thumb_up 649 thanks given
    3. group 113 followers
    1. forum 433 posts
    2. attach_file 15 attachments




Welcome to futures io: the largest futures trading community on the planet, with well over 125,000 members
  • Genuine reviews from real traders, not fake reviews from stealth vendors
  • Quality education from leading professional traders
  • We are a friendly, helpful, and positive community
  • We do not tolerate rude behavior, trolling, or vendors advertising in posts
  • We are here to help, just let us know what you need
You'll need to register in order to view the content of the threads and start contributing to our community.  It's free and simple.

-- Big Mike, Site Administrator

(If you already have an account, login at the top of the page)

Closed Thread
 
Search this Thread
 

KJ Trading Systems Kevin Davey - Ask Me Anything (AMA)

(login for full post details)
  #201 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


SMCJB View Post
Now I'm even more interested in who at ATASSN said that.

I'd be curious at what was actually said. As we have seen, second hand information can be misleading...

Follow me on Twitter
The following 2 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #202 (permalink)
Legendary Market Wizard
Houston, TX
 
Experience: Advanced
Platform: Trading Technologies
Broker: Primary Advantage Futures. Also ED&F and Tradestation
Trading: Primarily Energy but also a little GE, GC, SI & Bitcoin
 
Posts: 3,985 since Dec 2013
Thanks: 3,288 given, 7,799 received


kevinkdog View Post
I'd be curious at what was actually said. As we have seen, second hand information can be misleading...

Yeah good point.

 
(login for full post details)
  #203 (permalink)
Calgary
 
Experience: None
Platform: TradeStation, MT4
Trading: ES, Stocks
 
Posts: 73 since Aug 2015
Thanks: 4 given, 10 received

Kevin,

How do you use WFO in Multicharts? It seems to be quite confusing with Multicharts WFO results. What do you do with the results?

BTW, I use a tool because I believe in it. If I don't believe in a tool then I don't use it. This is my personal opinion. As for Andrea, he does not use it but he is planning to teach it. I have a problem with this!

 
(login for full post details)
  #204 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received

I'm confused. Your previous posts did nothing but question the usefulness of walkforward:

"several PhDs who believes that WFO is curve fitting at its best"

"pinnacle of curve fitting"

"He also does not believe in WFO"


Why then are you even interested in using it?

Follow me on Twitter
 
(login for full post details)
  #205 (permalink)
Calgary
 
Experience: None
Platform: TradeStation, MT4
Trading: ES, Stocks
 
Posts: 73 since Aug 2015
Thanks: 4 given, 10 received


kevinkdog View Post
I'm confused. Your previous posts did nothing but question the usefulness of walkforward:

"several PhDs who believes that WFO is curve fitting at its best"

"pinnacle of curve fitting"

"He also does not believe in WFO"


Why then are you even interested in using it?

I do believe in WFO but I came across several PhDs who do not believe in WFO. This is why I am confused. One of the PhDs claims that WFO is the pinnacle of curve fitting.

 
(login for full post details)
  #206 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


fiverr View Post
I do believe in WFO but I came across several PhDs who do not believe in WFO. This is why I am confused. One of the PhDs claims that WFO is the pinnacle of curve fitting.

I would suggest before you use WFO any further, you approach these multiple people, and find out their reasoning.

If you don't, and you still decide to use WF, there will be times WF doesn't work, and the voices of the doubters will fill your head with bad thoughts - at precisely the wrong time.

Ultimately, WF or no WF, you need to be as close to 100% confident in your process as you can, or you will not succeed in the long run.

Don't listen to me say "WF is good" - listen and try to understand those who say "WF is bad" and then weigh all the evidence, and make a decision if you want it as part of your development process. You'll be a much stronger trader/developer as a result, no matter if you use WF or not.

Follow me on Twitter
The following 4 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #207 (permalink)
Legendary Market Wizard
Houston, TX
 
Experience: Advanced
Platform: Trading Technologies
Broker: Primary Advantage Futures. Also ED&F and Tradestation
Trading: Primarily Energy but also a little GE, GC, SI & Bitcoin
 
Posts: 3,985 since Dec 2013
Thanks: 3,288 given, 7,799 received

Hey @kevinkdog, some free advertising for you.



Finally got around to watching the video of the "Stratergy Factory - Watch Me Develop a Trading Strategy" webinar that you did last month when I was on vacation. It was truely excellent. Having read your book and done your class, I think I had a good understanding of your method but watching you put it all into practice wrapped everything up perfectly for me. Now all I need to do, is put it into practice!

The following 3 users say Thank You to SMCJB for this post:
 
(login for full post details)
  #208 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


SMCJB View Post
Hey @kevinkdog, some free advertising for you.



Finally got around to watching the video of the "Stratergy Factory - Watch Me Develop a Trading Strategy" webinar that you did last month when I was on vacation. It was truly excellent. Having read your book and done your class, I think I had a good understanding of your method but watching you put it all into practice wrapped everything up perfectly for me. Now all I need to do, is put it into practice!


Thanks!

Glad you enjoyed the class! I look forward to helping you, and seeing the results of the strategies you create!

Kevin

Follow me on Twitter
The following user says Thank You to kevinkdog for this post:
 
(login for full post details)
  #209 (permalink)
San Tan Valley, AZ/USA
 
Experience: Advanced
Platform: NT7
Broker: IB, Tallinex, & 10 others.
Trading: Futures
 
FABRICATORX's Avatar
 
Posts: 195 since Jun 2013
Thanks: 697 given, 164 received


kevinkdog View Post
Thanks!

Glad you enjoyed the class! I look forward to helping you, and seeing the results of the strategies you create!

Kevin

You're a class act dude. Grateful I got to know you

Jimmy

-Jimmy
The following user says Thank You to FABRICATORX for this post:
 
(login for full post details)
  #210 (permalink)
Zurich, Switzerland
 
Experience: Advanced
Platform: Market Delta, Ninjatrader
Trading: Bund, 6E, FDAX, ES
 
Posts: 13 since Apr 2010
Thanks: 14 given, 15 received


SMCJB View Post
Hey @kevinkdog, some free advertising for you.



Finally got around to watching the video of the "Stratergy Factory - Watch Me Develop a Trading Strategy" webinar that you did last month when I was on vacation. It was truely excellent. Having read your book and done your class, I think I had a good understanding of your method but watching you put it all into practice wrapped everything up perfectly for me. Now all I need to do, is put it into practice!


hi Kevin, i have read your book and it was excellent!
i was wondering where i could find the recording of the above mentioned video (Strategy factory - watch me develop a trading strategy)? is that a public video like the others?

 
(login for full post details)
  #211 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


Swisstrader1 View Post
hi Kevin, i have read your book and it was excellent!
i was wondering where i could find the recording of the above mentioned video (Strategy factory - watch me develop a trading strategy)? is that a public video like the others?

Glad you enjoyed the book!

Sorry, that video is for my student traders only...

If you e-mail me a copy of your book invoice, though, I will send you some free book bonuses.

kdavey ay kjtraidngsystems.com

Follow me on Twitter
 
(login for full post details)
  #212 (permalink)
boston massachusetts/usa
 
 
Posts: 7 since Sep 2016
Thanks: 1 given, 1 received

Sounds interesting. I to am interested

 
(login for full post details)
  #213 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


dmwangi16 View Post
Sounds interesting. I to am interested

Thanks for the comment...

Interested in what exactly?

Follow me on Twitter
The following user says Thank You to kevinkdog for this post:
 
(login for full post details)
  #214 (permalink)
Site Moderator
London UK
 
Experience: Beginner
Platform: CQG
Broker: S5
Trading: Futures
 
xplorer's Avatar
 
Posts: 5,306 since Sep 2015
Thanks: 13,351 given, 12,653 received


dmwangi16 View Post
Sounds interesting. I to am interested

Seen this generic comment elsewhere from this new user. Are you a bot?

 
(login for full post details)
  #215 (permalink)
boston massachusetts/usa
 
 
Posts: 7 since Sep 2016
Thanks: 1 given, 1 received

I am not a bit. Just a inquisitive reader.

Sent using the futures.io mobile app

 
(login for full post details)
  #216 (permalink)
boston massachusetts/usa
 
 
Posts: 7 since Sep 2016
Thanks: 1 given, 1 received

I read on another post how you created some good systems

Sent using the futures.io mobile app

 
(login for full post details)
  #217 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


dmwangi16 View Post
I read on another post how you created some good systems

Sent using the futures.io mobile app

There are a bunch of archived webinars I did that are available for you to view. Those are free (you might have to be Elite member), but that is a good place to start. My website also has a bunch of free info.

Follow me on Twitter
The following user says Thank You to kevinkdog for this post:
 
(login for full post details)
  #218 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


dmwangi16 View Post
I read on another post how you created some good systems

Sent using the futures.io mobile app

Hi @dmwangi16 -

Were you able to find some information?

Kevin

Follow me on Twitter
 
(login for full post details)
  #219 (permalink)
sweden
 
Experience: Advanced
Platform: NinjaTrader,MetaTrader
Trading: futures, FX
 
Mabi's Avatar
 
Posts: 141 since Oct 2010
Thanks: 121 given, 135 received

Kevin

Is it better to use the total portfolios performance to dictate the increase of lot size or is it rather better to implement that individually on each strategy's performance. This can be done automatically and allow for a type of compounding of the profits if done in % allowed risk per trade and account current balance. So far I have been doing it individually but can see that some strategies takes of and some do not and might never catch up which in away offsets the balance of the portfolio.

The following user says Thank You to Mabi for this post:
 
(login for full post details)
  #220 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


Mabi View Post
Kevin

Is it better to use the total portfolios performance to dictate the increase of lot size or is it rather better to implement that individually on each strategy's performance. This can be done automatically and allow for a type of compounding of the profits if done in % allowed risk per trade and account current balance. So far I have been doing it individually but can see that some strategies takes of and some do not and might never catch up which in away offsets the balance of the portfolio.

You could do it either way, but you are right in that you likely want to remain balanced between all strategies. Who knows if your best performing strat in 2016 will still be best in 2017? Being balanced mitigates this possibility.

So, I'd probably say using fixed fractional approach, based on total account equity, is a good (better?) way to go...

Follow me on Twitter
The following 2 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #221 (permalink)
sweden
 
Experience: Advanced
Platform: NinjaTrader,MetaTrader
Trading: futures, FX
 
Mabi's Avatar
 
Posts: 141 since Oct 2010
Thanks: 121 given, 135 received

Hi Kevin ,

Thanks again for your previous answer. Now something came up that are related to previous question. When Building portfolios i see that some strategies from some instruments are dominating. Now it is no problem if they do as long as they perform but if they do not perform it becomes a problem. Below you see some live traded results from a portfolio that have been running for i think 8 weeks or maybe 9 (160 trades). The 2 strategies on the far right are gold and they have hurt the performance badly even thought totally it is still in about 9% profit this morning . When building a portfolio what should i do. Remove the dominating strategies or leave them in. Or maybe instead change and individualize the moneymanagement from the start to even them up as per their historical performance.

If the two strategies on the right would have been winning it would actually also look strange since then the other strategies profits would have been really small in comparison.



Thanks

The following user says Thank You to Mabi for this post:
 
(login for full post details)
  #222 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


Mabi View Post
Hi Kevin ,

Thanks again for your previous answer. Now something came up that are related to previous question. When Building portfolios i see that some strategies from some instruments are dominating. Now it is no problem if they do as long as they perform but if they do not perform it becomes a problem. Below you see some live traded results from a portfolio that have been running for i think 8 weeks or maybe 9. The 2 strategies on the far right are gold and they have hurt the performance badly even thought totally it is still in about 9% profit this morning . When building a portfolio what should i do. Remove the dominating strategies or leave them in. Or maybe instead change and individualize the money management from the start to even them up as per their historical performance.

If the two strategies on the right would have been winning it would actually also look strange since then the other strategies profits would have been really small in comparison.



Thanks


The answer to the question "what should I do" depends a lot on what you want to accomplish with the portfolio. Are you going for max returns, or maybe minimum drawdown, or smooth equity curve, or excellent return/drawdown ratio, etc.

Once you figure out what your goal is, you can examine the pieces of your portfolio, and construct a portfolio to meet your goals. Maybe Gold should be taken out, or maybe you should trade mini Gold. Or maybe you trade 2 or 3 contracts of everything else to 1 contract of Gold. Or maybe you just have a heavily weighted Gold portfolio, which maybe offsets some other investments you have.

I hope you see the point - what you have found is something correctable, but only if you know where you want to get to.

Follow me on Twitter
The following 3 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #223 (permalink)
Legendary Market Wizard
Houston, TX
 
Experience: Advanced
Platform: Trading Technologies
Broker: Primary Advantage Futures. Also ED&F and Tradestation
Trading: Primarily Energy but also a little GE, GC, SI & Bitcoin
 
Posts: 3,985 since Dec 2013
Thanks: 3,288 given, 7,799 received

Great question @Mabi, I'm only trading a few systems (as a systematic trader) and have found a similar situation with one system dominating prtfolio performance.


kevinkdog View Post
Or maybe you trade 2 or 3 contracts of everything else to 1 contract of Gold.

Assuming your confident in the system I think this is the best answer... but only if you have the capital to do it.!

The following user says Thank You to SMCJB for this post:
 
(login for full post details)
  #224 (permalink)
sweden
 
Experience: Advanced
Platform: NinjaTrader,MetaTrader
Trading: futures, FX
 
Mabi's Avatar
 
Posts: 141 since Oct 2010
Thanks: 121 given, 135 received


SMCJB View Post
Great question @Mabi, I'm only trading a few systems (as a systematic trader) and have found a similar situation with one system dominating prtfolio performance.

Assuming your confident in the system I think this is the best answer... but only if you have the capital to do it.!

Thanks Kevin and SMCJB,

Comparing with how you run a company you never want your whole existence depend on one or 2 costumers and you would like to be able to budget next years result but you still want the profit from the highvalue cotumers though but they shall not be able to pull you down if they leave. So i guess i will try to even them out in some way prefeably increasing contract size on the lesser performers,

 
(login for full post details)
  #225 (permalink)
Luxembourg, Luxembourg
 
Experience: Advanced
Platform: TWS
Broker: Interactive Brokers
Trading: Stocks
 
Posts: 491 since May 2012
Thanks: 1,641 given, 1,149 received


Mabi View Post
Hi Kevin ,

Thanks again for your previous answer. Now something came up that are related to previous question. When Building portfolios i see that some strategies from some instruments are dominating. Now it is no problem if they do as long as they perform but if they do not perform it becomes a problem. Below you see some live traded results from a portfolio that have been running for i think 8 weeks or maybe 9 (160 trades). The 2 strategies on the far right are gold and they have hurt the performance badly even thought totally it is still in about 9% profit this morning . When building a portfolio what should i do. Remove the dominating strategies or leave them in. Or maybe instead change and individualize the moneymanagement from the start to even them up as per their historical performance.

If the two strategies on the right would have been winning it would actually also look strange since then the other strategies profits would have been really small in comparison.

Thanks

I can't answer the decision of whether to include or exclude systems, but I can give some insight into portfolio allocation methodologies that you could use. When I was still trading a suite of systems, I used either one of the following methods to assign risk / weightings to my systems.
  1. You can view your systems as independent systems and allocate capital evenly across them at the beginning. The benefit of this method is that winning systems will have a greater allocation of capital and losing systems will have a smaller allocation of capital as time progresses.
  2. You can view your systems as all part of one portfolio and constant re-weight them. An easy way to do this is to always risk x% per trade of your total portfolio value. Downsides are the opposite of the positives of the independent system approach, but when a system starts to become profitable it recovers losses much quicker.

If you wish, you could also add drawdown-reducing techniques to both methods. Some drawdown-reducing techniques are things like a) halve size every with every 10% in drawdown and bring it back only once you recover the drawdown-threshold, b) halve size after winning % drops to x%, or c) halve size after a certain number of losing trades in a row. You would need to keep track of the individual metrics of each system for this to work.

Final thought - with regards to gold dominating your portfolio - if you are basing your stop-loss (and then sizing your positions accordingly) on ATR or something similar, then the allocation to gold should be equal to an allocation to treasuries. I am guessing here, but I would suspect that your sizing on gold is larger than it should be in terms of ATR. If that is the case, you need to evaluate whether the added risk is worth it to you. If not, then you need to use Kevin's criteria to determine whether it should still be included.

The following 3 users say Thank You to grausch for this post:
 
(login for full post details)
  #226 (permalink)
sweden
 
Experience: Advanced
Platform: NinjaTrader,MetaTrader
Trading: futures, FX
 
Mabi's Avatar
 
Posts: 141 since Oct 2010
Thanks: 121 given, 135 received

@grausch
Thanks again for your reply !!. I have been busy at work but I had time to shortly after your post lowered the contract size on the less performing strategies and increased them equally on the performing ones.

System shortly after went in to a drawdown and Gold kept loosing but with last couple of days due to increased volatility portfolio has been doing pretty well and even though Gold has continued to loose it's impact is now much less on the portfolio as you can see from the screen dump. I might ditch the Gold if it keeps loosing but it is not time for that yet due to it's historical performance. Portfolio has now done around 330 trades since October 10. I plan to launch 2 more portfolios by January 1 and if I find time I might start a thread how I did it. However I rather start a thread if it is doing good with some longer history.


The following user says Thank You to Mabi for this post:
 
(login for full post details)
  #227 (permalink)
Tel Aviv Israel
 
Experience: Beginner
Platform: NinjaTrader
Broker: CQG
Trading: Futures
 
Posts: 21 since Feb 2015
Thanks: 30 given, 13 received

Hi Kevin,
First I would like to thank you for taking the time to answer many posts very thoroughly.

I apologize in advanced if the following has been discussed here before but the thread is getting large

When optimizing a system there are a few types of strategy parameters. There are parameters you wish to check for a wide range of values and there are parameters that you only want to check 2-3 values. Sometimes it can be an "on off" switch parameter.

Do I need to differentiate between those types of parameters while determining the minimum trade count that is sufficient per in sample? In your book you say that 30 trades per parameter is sufficient, is it true for "on off" switches as well?

Another thing I was wondering about, if I am optimizing an intraday strategy and I do have more than enough trades for "avoiding overfitting" in 3 months, should I use more in sample data just in order to avoid optimizing (or exploring the idea) in the in sample to a certain "state" of the market which can pass shortly (like a 30 days of trend for instance)?

And one last subject I have issues with, should the data that I explore my strategy initially be a part of the in sample in a walk forward optimization?
You wrote before about not to try to optimize the backtest but if I do optimize by adding more filters (in the first in sample) and still have enough trades per parameter is it OK? Will the walk forward tell me the answer or should I avoid running too many walk forward optimizations in order not to look too much at the out of sample data?

Thanks in advanced!

 
(login for full post details)
  #228 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


ToMerK View Post
Hi Kevin,
First I would like to thank you for taking the time to answer many posts very thoroughly.

I apologize in advanced if the following has been discussed here before but the thread is getting large

When optimizing a system there are a few types of strategy parameters. There are parameters you wish to check for a wide range of values and there are parameters that you only want to check 2-3 values. Sometimes it can be an "on off" switch parameter.

Do I need to differentiate between those types of parameters while determining the minimum trade count that is sufficient per in sample? In your book you say that 30 trades per parameter is sufficient, is it true for "on off" switches as well?

I have never treated those as different, but I guess you could. Remember though that the 30 number is just a rule of thumb, ideally you'd want 50 or more. So, I'd be conservative and treat on/off the same as any other.


Quoting 
Another thing I was wondering about, if I am optimizing an intraday strategy and I do have more than enough trades for "avoiding overfitting" in 3 months, should I use more in sample data just in order to avoid optimizing (or exploring the idea) in the in sample to a certain "state" of the market which can pass shortly (like a 30 days of trend for instance)?

I would definitely test an intraday strategy over more than 3 months. You want something that works over the long haul, with a lot of different market conditions. You only see limited market conditions in 3 months.


Quoting 
And one last subject I have issues with, should the data that I explore my strategy initially be a part of the in sample in a walk forward optimization?
You wrote before about not to try to optimize the backtest but if I do optimize by adding more filters (in the first in sample) and still have enough trades per parameter is it OK? Will the walk forward tell me the answer or should I avoid running too many walk forward optimizations in order not to look too much at the out of sample data?

Thanks in advanced!

I usually leave the initial exploration time period in the walkforward. I would try running one walkforward optimization, and that is it. Everytime you make a change and rerun the walkforward, you are getting less and less "out of sample - ness". Rerun walkforward enough and you get an in-sample test. So be careful here.

Follow me on Twitter
The following 3 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #229 (permalink)
Tel Aviv Israel
 
Experience: Beginner
Platform: NinjaTrader
Broker: CQG
Trading: Futures
 
Posts: 21 since Feb 2015
Thanks: 30 given, 13 received

Thanks you Kevin for taking the time to answer.

One other thing I have a problem with is that when we are testing over a few years an intraday strategy it means that we disqualify the possibility of new strategies that become relevant only in the last few months. For example, recently the iceberg orders in forex futures were cancelled. After such an event new strategies that take advantage of level 2 that were not valid before can suddenly have a merit. Should I not test these kind of strategies only because I do not have a few years to test on?

Also, if my strategy has only 3-4 ticks of target per trade, the "trendiness" or many of the other "states" of the market do not effect it. So a strategy like that cannot be optimized over a period of 3 months or so (with ~50 trades per parameter)?

About the walk forward optimization, if I make on walk forward run, discover I overfitted the data, remove one filter and rerun it, will it be valid?

If I make an agreement with myself not to look at the results thoroughly, only look at the cumulative profit graphs and if they do not satisfy me I will readjust the strategy, does it hurt the out of sampleness? I will not derive anything from the out of sample data but the shape of this specific graph.

The following user says Thank You to ToMerK for this post:
 
(login for full post details)
  #230 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


ToMerK View Post
Thanks you Kevin for taking the time to answer.

One other thing I have a problem with is that when we are testing over a few years an intraday strategy it means that we disqualify the possibility of new strategies that become relevant only in the last few months. For example, recently the iceberg orders in forex futures were cancelled. After such an event new strategies that take advantage of level 2 that were not valid before can suddenly have a merit. Should I not test these kind of strategies only because I do not have a few years to test on?

Also, if my strategy has only 3-4 ticks of target per trade, the "trendiness" or many of the other "states" of the market do not effect it. So a strategy like that cannot be optimized over a period of 3 months or so (with ~50 trades per parameter)?

About the walk forward optimization, if I make on walk forward run, discover I overfitted the data, remove one filter and rerun it, will it be valid?

If I make an agreement with myself not to look at the results thoroughly, only look at the cumulative profit graphs and if they do not satisfy me I will readjust the strategy, does it hurt the out of sampleness? I will not derive anything from the out of sample data but the shape of this specific graph.


Of course you can do all these things if you want to. I personally don't, but that doesn't mean you can't. The big keys to strategy development:

1) develop strategies in a way that you feel comfortable with
2) validate your approach with real money trading, and adjust your approach as necessary.

I know other traders who laugh at and tease me about my development process. They do things differently, and if it works for them, who am I to judge? I do what works for me. You should do what works for you.

Follow me on Twitter
The following 4 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #231 (permalink)
Tel Aviv Israel
 
Experience: Beginner
Platform: NinjaTrader
Broker: CQG
Trading: Futures
 
Posts: 21 since Feb 2015
Thanks: 30 given, 13 received


kevinkdog View Post
Of course you can do all these things if you want to. I personally don't, but that doesn't mean you can't. The big keys to strategy development:

1) develop strategies in a way that you feel comfortable with
2) validate your approach with real money trading, and adjust your approach as necessary.

I know other traders who laugh at and tease me about my development process. They do things differently, and if it works for them, who am I to judge? I do what works for me. You should do what works for you.

Thanks for the reply.

As I am searching for the right method to test the validity of my strategies I am trying not to make mistakes that others documented before in order to make the process less painful. Because you have your way of doing things and it has been proven over the years I highly value your opinion.

The thing I am trying to understand is if the rules can be broken, which that is what you said in the last post. Others do succeed with other rules or less strict rules.

I read you only relatively recently started developing strategies for intraday trading, correct if I am wrong. Do you see the same results as swing trading? Do the equity curves continue as expected in real money?

 
(login for full post details)
  #232 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


ToMerK View Post
Thanks for the reply.

As I am searching for the right method to test the validity of my strategies I am trying not to make mistakes that others documented before in order to make the process less painful. Because you have your way of doing things and it has been proven over the years I highly value your opinion.

The thing I am trying to understand is if the rules can be broken, which that is what you said in the last post. Others do succeed with other rules or less strict rules.

I read you only relatively recently started developing strategies for intraday trading, correct if I am wrong. Do you see the same results as swing trading? Do the equity curves continue as expected in real money?

In general, I find intraday strategy creation much tougher than swing strategies. Maybe that is because of the development approach I use. I find that intraday strats many times do work the same going forward as swing strategies, so I've not seen a huge difference.

Follow me on Twitter
The following 2 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #233 (permalink)
Espoo Finland
 
Experience: Intermediate
Platform: TradingBlox
Trading: Stocks
 
Posts: 35 since Sep 2015
Thanks: 0 given, 10 received

When developing strategies in the beginning phase I test my "raw" strategy on a portfolio of markets. I then reject the markets where there results are bad and only use the strategy on markets that are good.

I am wondering whether this is the best way to go about it. I wonder whether I should just test and optimize the strategy on one market at a time.

I'm worried of curve fitting if I test on one market at a time. However I'm also worried that by rejecting some markets from my strategy porfolio, I am also making things look nicer than they are in backtesting.

 
(login for full post details)
  #234 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


bluefightingcat View Post
When developing strategies in the beginning phase I test my "raw" strategy on a portfolio of markets. I then reject the markets where there results are bad and only use the strategy on markets that are good.

I am wondering whether this is the best way to go about it. I wonder whether I should just test and optimize the strategy on one market at a time.

I'm worried of curve fitting if I test on one market at a time. However I'm also worried that by rejecting some markets from my strategy porfolio, I am also making things look nicer than they are in backtesting.


If you do it correctly, you could do one market at a time without curve fitting. But, you could also easily do it improperly and curve fit.

By eliminating markets, you are definitely cherry picking, and your forward results will be nowhere as good.

I have some webinars here that might help you with your test approach. I recommend you watch.


THANKS!

Follow me on Twitter
The following 2 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #235 (permalink)
Espoo Finland
 
Experience: Intermediate
Platform: TradingBlox
Trading: Stocks
 
Posts: 35 since Sep 2015
Thanks: 0 given, 10 received

I'm looking into trading futures. My intention is to trade futures on a daily timeframe. However, I am worried that one day an overnight gap might happen (black swan or something) and because of the huge leverage involved, I'd be wiped out.

Do you have any experience with this? Do you have any advice on how to protect myself from such a situation?

The following user says Thank You to bluefightingcat for this post:
 
(login for full post details)
  #236 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received

Black Swans happen, and they can be brutal.

There is no "cure" for overnight risk - whenever you have positions in the market, you run the risk of something really bad happening.

You can have stop orders submitted, but they might not protect you in the case of a flash crash situation. They may actually be worse for you sometimes.

You could hedge your position with options, but that comes with a cost.

Really, the biggest thing might be to limit your size and leverage.

There is no great answer here - you just have to decide how much risk you can handle, and decide on an appropriate course of action.

Follow me on Twitter
The following user says Thank You to kevinkdog for this post:
 
(login for full post details)
  #237 (permalink)
Illinois
 
Experience: Intermediate
Trading: Futures
 
Posts: 56 since Apr 2015
Thanks: 72 given, 16 received

The workshop looks interesting. On the website, there is a section called "The Proof Is In The Pudding" with information about a diversified system that trades via Striker. I trust Striker. The overall % gain seems good, but in looking at the performance in more detail the equity curved peaked in February 2016 and has been in drawdown since that month (pretty much a full year out of the 17.5 months it has been tracked).

Now, a lot of systems perform that way and come back up. But this is a diversified system, trading multiple markets, so I would have hoped for a smoother equity curve, with shorter drawdown periods. Am I looking at this wrong?

The following user says Thank You to gumdr0p for this post:
 
(login for full post details)
  #238 (permalink)
Illinois
 
Experience: Intermediate
Trading: Futures
 
Posts: 56 since Apr 2015
Thanks: 72 given, 16 received

Digging deeper on Striker, there are two more KJ systems.

One has a return of -52% over more than a year... and the other doesn't show results (which isn't uncommon for newer systems on Striker).

I'm just not feeling a lot of confidence in purchasing the workshop. Am I missing something?

The following user says Thank You to gumdr0p for this post:
 
(login for full post details)
  #239 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


gumdr0p View Post
The workshop looks interesting. On the website, there is a section called "The Proof Is In The Pudding" with information about a diversified system that trades via Striker. I trust Striker. The overall % gain seems good, but in looking at the performance in more detail the equity curved peaked in February 2016 and has been in drawdown since that month (pretty much a full year out of the 17.5 months it has been tracked).

Now, a lot of systems perform that way and come back up. But this is a diversified system, trading multiple markets, so I would have hoped for a smoother equity curve, with shorter drawdown periods. Am I looking at this wrong?

Thanks for the comment. The only odd thing that Striker does is that is shows the results of closed trades only. It does not include open equity. Since some of the systems here have rather long trade lengths, it distorts the results a bit.

When you include the impact of open equity (marked to market accounting), I show the last peak for Diversified A to be in October - so the system has spent the last 4 months in drawdown. It is currently in a drawdown right now.

So, yes, while the Diversified A system has nice gains nice inception, the last few months have been blah. In my experience that is not uncommon. Most of the time systems are in one kind of drawdown or another.

Follow me on Twitter
The following user says Thank You to kevinkdog for this post:
 
(login for full post details)
  #240 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


gumdr0p View Post
Digging deeper on Striker, there are two more KJ systems.

One has a return of -52% over more than a year... and the other doesn't show results (which isn't uncommon for newer systems on Striker).

I'm just not feeling a lot of confidence in purchasing the workshop. Am I missing something?


Yes unfortunately that portfolio (Diversified II) has not been doing well.Most of the loss was due to an ES strategy, which has since been replaced. But performance still lags.

I'm not sure how to increase your confidence level. I can say that after you learn the techniques I teach in the workshop, success with developing strategies will be mainly up to you. You will have the tools to develop strategies as good as, or better than, the ones I offer thru Striker. You'll probably also develop strategies that fail - that is all part of the process.

If you PM me, I can put you in touch with other students, who can give you the pros and cons of the workshop.

Thanks!
Kevin

Follow me on Twitter
 
(login for full post details)
  #241 (permalink)
Illinois
 
Experience: Intermediate
Trading: Futures
 
Posts: 56 since Apr 2015
Thanks: 72 given, 16 received

Kevin, thanks for the responses. I'm also looking at the systems over on C2. I realize not all can be good and profitable.... but which ones would be representative proof that one can develop successful trading systems via your methodology?

The following user says Thank You to gumdr0p for this post:
 
(login for full post details)
  #242 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


gumdr0p View Post
Kevin, thanks for the responses. I'm also looking at the systems over on C2. I realize not all can be good and profitable.... but which ones would be representative proof that one can develop successful trading systems via your methodology?

I am not active at C2 any longer. But last time I checked, I had 20 strategies at Collective2. 15 of those are profitable. Some (most?) of them had high percentage drawdowns, mainly because of the extreme leverage I used. Many people at that site like high risk/high reward scenarios.

In general, based on how I develop systems, I consider it good to have return/drawdown ratios of 2.0 (meaning if you want 50% annual return, you have to endure 25% drawdowns along the way). That is the benchmark in my own trading.

As a point of reference, most Commodity Trading Advisors (CTAs) like to have a return/drawdown of 1.0. But then again, they have objectives and priorities that retail traders like you and I don't have...

Follow me on Twitter
The following 3 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #243 (permalink)
Legendary Market Wizard
Houston, TX
 
Experience: Advanced
Platform: Trading Technologies
Broker: Primary Advantage Futures. Also ED&F and Tradestation
Trading: Primarily Energy but also a little GE, GC, SI & Bitcoin
 
Posts: 3,985 since Dec 2013
Thanks: 3,288 given, 7,799 received


gumdr0p View Post
Digging deeper on Striker, there are two more KJ systems.

One has a return of -52% over more than a year... and the other doesn't show results (which isn't uncommon for newer systems on Striker).

I'm just not feeling a lot of confidence in purchasing the workshop. Am I missing something?

I'm a career energy trader, now an individual proprietary trader. My trading style is very spread, arbitrage and statistical based - and not systematic trading like many here - or what Kevin trades and teaches. I'm always trying to improve myself, and learn new things about the industry. Hence I always found Kevin's post's (and Book) to be interesting and informative. Last spring, when things were very quiet for me, I took Kevin's day class. I did this, not with the intention of becoming a systematic trader, but just as education for myself.

I found the class to be well taught and the subjective matter very interesting. I am somebody who would much rather sit down with a laptop and try and solve a problem/code something/research something traded related than watch TV. Hence I found myself coming back to Kevin's material again and again. In August I finally went live with a new account at Tradestation and started trading a couple of systems. The next four months were mostly sideways (did have a month long drawdown in October) but in December I finally set (two) meaningful account high water marks. This month things have continued to be good and I can honestly say that my account as of close Friday night set a new high water mark. While this isn't a huge amount of money, it is enough to pay for Kevin's course many times over. If it wasn't for some newbee automated trading mistakes I'd be even higher.

If you'd like more comments on the course take a look at this thread. Vendor Review: KJ Trading Systems Strategy Factory


kevinkdog View Post
In general, based on how I develop systems, I consider it good to have return/drawdown ratios of 2.0 (meaning if you want 50% annual return, you have to endure 25% drawdowns along the way). That is the benchmark in my own trading.

As a point of reference, most Commodity Trading Advisors (CTAs) like to have a return/drawdown of 1.0. But then again, they have objectives and priorities that retail traders like you and I don't have...

Before my October draw down I was at 1.45x, and as of Friday night I'm at 1.62x and optimistic about getting to 2.0x soon.

Full Disclaimer: While I have talked and emailed with Kevin many times, I do not know him personally and did actually meet him here at futures.io. Other than being somebody who paid to attend his course I have no financial relationship with Kevin. In other words, while I may seem to be his cheerleader, I'm actually just a happy customer.

The following 6 users say Thank You to SMCJB for this post:
 
(login for full post details)
  #244 (permalink)
Illinois
 
Experience: Intermediate
Trading: Futures
 
Posts: 56 since Apr 2015
Thanks: 72 given, 16 received


SMCJB View Post
.
If you'd like more comments on the course take a look at this thread. Vendor Review: KJ Trading Systems Strategy Factory

Before my October draw down I was at 1.45x, and as of Friday night I'm at 1.62x and optimistic about getting to 2.0x soon.

Nice. Reading the thread, it sounds grueling but possible to suffer through the drawdowns and remain profitable (I wonder what happened to @risingfire ?). One question on my mind in considering this style of system development, is how much time would I need to devote? I already program a bit (a little Sierra and Ninja, plus non-trading stuff), and have been doing stuff in the markets for years at an amateur level. But given that I want to maintain another occupation that I love, what is the minimum I'd need to plan if I wanted to develop systems using this approach?

The following user says Thank You to gumdr0p for this post:
 
(login for full post details)
  #245 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


gumdr0p View Post
Nice. Reading the thread, it sounds grueling but possible to suffer through the drawdowns and remain profitable (I wonder what happened to @risingfire ?). One question on my mind in considering this style of system development, is how much time would I need to devote? I already program a bit (a little Sierra and Ninja, plus non-trading stuff), and have been doing stuff in the markets for years at an amateur level. But given that I want to maintain another occupation that I love, what is the minimum I'd need to plan if I wanted to develop systems using this approach?

It is grueling. There is no shortcut to successful trading, regardless of what the knuckleheads selling snake oil tell you. If you can spend 10 hours a week, I think in a few months after the workshop you could have 1-3 strategies that might be tradeable (after all evaluations are complete). But, there are so many variables it is hard to tell. I have had students produce multiple strategies within a month of attending, and I'm sure others struggle for months and give up without producing any.

@risingfire is still an active member, and he still submits strategies to the Strategy Factory Club (a great way to build up your strategy library).


I will say this: if you are committed, and not easily defeated, you can do well. But, if you are the type of person who needs to see instant results (or you give up), trading is likely not a good endeavor for you.

Follow me on Twitter
The following 5 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #246 (permalink)
Illinois
 
Experience: Intermediate
Trading: Futures
 
Posts: 56 since Apr 2015
Thanks: 72 given, 16 received


kevinkdog View Post
In general, based on how I develop systems, I consider it good to have return/drawdown ratios of 2.0 (meaning if you want 50% annual return, you have to endure 25% drawdowns along the way). That is the benchmark in my own trading.

If you have multiple systems and they all eventually do poorly (according to your website) .. does that mean that they run ideally at 2.0 and then eventually drift down to a point where you turn them off? If that's the case, what ratio do you end up with overall w/ diversification between systems continuing at 2.0 and others faltering?

The following user says Thank You to gumdr0p for this post:
 
(login for full post details)
  #247 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


gumdr0p View Post
If you have multiple systems and they all eventually do poorly (according to your website) .. does that mean that they run ideally at 2.0 and then eventually drift down to a point where you turn them off? If that's the case, what ratio do you end up with overall w/ diversification between systems continuing at 2.0 and others faltering?

The return/dd ratio is calculated over a number of years, and is highly variable from period to period. When you add all systems up, if you end up with >2 over a long period of time, you are doing pretty well. But sometimes you will be worse than that, other times you will be a lot better than that.

The big key here is that you have a plan/approach with the idea that each strategy will eventually fail. That doesn't mean they will, but as the saying goes "it is better to plan for failure, than failing to plan."

Follow me on Twitter
The following 2 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #248 (permalink)
Raliegh, NC
 
Experience: Intermediate
Platform: Tradestation, Multicharts
Broker: Tradestation, Interactive Brokers
Trading: Several
 
Posts: 31 since Apr 2014
Thanks: 104 given, 91 received


kevinkdog View Post
It is grueling. There is no shortcut to successful trading, regardless of what the knuckleheads selling snake oil tell you. If you can spend 10 hours a week, I think in a few months after the workshop you could have 1-3 strategies that might be tradeable (after all evaluations are complete). But, there are so many variables it is hard to tell. I have had students produce multiple strategies within a month of attending, and I'm sure others struggle for months and give up without producing any.

@risingfire is still an active member, and he still submits strategies to the Strategy Factory Club (a great way to build up your strategy library).


I will say this: if you are committed, and not easily defeated, you can do well. But, if you are the type of person who needs to see instant results (or you give up), trading is likely not a good endeavor for you.

I want to +1 everything Kevin said. Maintaining my course and objective has taken incredible inner reserves and fortitude. I have had to change my expectations over and over again and work with my emotional fear responses. I've had to change course in approach so many times in order to weed out my bad habits that it feels like I've recreated myself several times over. It has taken boat loads of perseverance and commitment. My challenges will not be your own, but I still consider all the difficulties last year to be of great benefit and value. Many of my strategies still fail the 6-month club test. I'm probably not doing anything good for his club success rate averages (Sorry, Kevin... I continue to try! )

So there are many challenges along the way, but it IS doable. I believe that I have a sustaining and profitable system now and am developing the means to continue forward development. Time will tell.

The following 4 users say Thank You to risingfire for this post:
 
(login for full post details)
  #249 (permalink)
Houston
 
 
Posts: 176 since Dec 2016
Thanks: 98 given, 97 received

Hello Kevin,

I am currently enjoying you book as I want to be a more systematic manual day trader with my current system or idea systems.

I would like to know will your book help me with manually back testing my trading ideas vs programming the trading idea and then back testing. Eventually, I do plan to start learning to program via Tradestation.

I have not moved to programming yet cause my mind is still stuck in manually day trading my systematic trading plan, however, I never thoroughly and properly back tested the system or even kept a journal. I am now doing this.

I trade resistance and supports from a service I pay monthly to obtain the resistance and supports. So I do not know how to program the resistance and supports and back test them. Of course the vendor will not share how they calculate these daily resistance and supports. Also, I never used indicators, just price action what i see on the chart. For example, if I see price going up, I get ready to go long per my entry rules. However, I can not program my eyes. So I am not familiar with indicators, I just manually trade the charts for the past 2 years. I have been paper trading for 1.5 years.

Manually back testing is labor intensive, but I guess I am being stubborn and not wanting to give up on my current system, yet the reason I purchase your book was to learn how to properly back test a system and trade the system statistically confidence. But all I know is support, resistance, trend lines and identify trends with my eyes. I am breakout trader. But I saw one of your webinar and it states sometimes it takes 100 - 200 trading ideas before finding one system that may work going forward. And here I am still stuck on one trading system for nearly 1 year.

I appreciate any suggestions, opinions, comments, or questions you have for me. And really appreciate your time and effort in the response. Great Book.

Thank you

 
(login for full post details)
  #250 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


goodoboy View Post
Hello Kevin,

I am currently enjoying you book as I want to be a more systematic manual day trader with my current system or idea systems.

I would like to know will your book help me with manually back testing my trading ideas vs programming the trading idea and then back testing. Eventually, I do plan to start learning to program via Tradestation.

I have not moved to programming yet cause my mind is still stuck in manually day trading my systematic trading plan, however, I never thoroughly and properly back tested the system or even kept a journal. I am now doing this.

I trade resistance and supports from a service I pay monthly to obtain the resistance and supports. So I do not know how to program the resistance and supports and back test them. Of course the vendor will not share how they calculate these daily resistance and supports. Also, I never used indicators, just price action what i see on the chart. For example, if I see price going up, I get ready to go long per my entry rules. However, I can not program my eyes. So I am not familiar with indicators, I just manually trade the charts for the past 2 years. I have been paper trading for 1.5 years.

Manually back testing is labor intensive, but I guess I am being stubborn and not wanting to give up on my current system, yet the reason I purchase your book was to learn how to properly back test a system and trade the system statistically confidence. But all I know is support, resistance, trend lines and identify trends with my eyes. I am breakout trader. But I saw one of your webinar and it states sometimes it takes 100 - 200 trading ideas before finding one system that may work going forward. And here I am still stuck on one trading system for nearly 1 year.

I appreciate any suggestions, opinions, comments, or questions you have for me. And really appreciate your time and effort in the response. Great Book.

Thank you

Thanks for the comment and questions. You are stuck in "no man's land" - you are afraid to let go of your current method, yet you feel a pull to do things differently.

I can tell you that the way you are currently trading is nearly impossible to test, given all the nuances with your current approach.

To be successful with algorithms, you have to be able to program every part of the strategy. It does not sound like you can do that now. You also have to program a lot of strategies (because most turn out to be junk). Then, to test manually is cumbersome, and really a non-starter. You'll never really get traction.



So, my advice - stick with your current trading method if it is working. If it is not, then maybe make a clean break and try something else, like algorithmic with proper development and testing. Don;t try to keep the old, and add the new. I don't see it working.

Follow me on Twitter
The following 4 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #251 (permalink)
Houston
 
 
Posts: 176 since Dec 2016
Thanks: 98 given, 97 received


kevinkdog View Post
Thanks for the comment and questions. You are stuck in "no man's land" - you are afraid to let go of your current method, yet you feel a pull to do things differently.

I can tell you that the way you are currently trading is nearly impossible to test, given all the nuances with your current approach.

To be successful with algorithms, you have to be able to program every part of the strategy. It does not sound like you can do that now. You also have to program a lot of strategies (because most turn out to be junk). Then, to test manually is cumbersome, and really a non-starter. You'll never really get traction.



So, my advice - stick with your current trading method if it is working. If it is not, then maybe make a clean break and try something else, like algorithmic with proper development and testing. Don;t try to keep the old, and add the new. I don't see it working.

Thank you kevinkdog for the response, Good advice and simple.

Your advice is the same thing I have been thinking about over the last month or two. It is a bit of thinking of circles, but part of this trading business, I am learning is make good decisions about going forward, before losing alot of time.

You nailed my current situation with accuracy. At least I now know my where my challenges are and have some suggestions on a path forward. And most important, at least I have a path forward on the right way to properly develop and test a trading strategy. I guess I fear letting go of existing trading approach, is because that's all I know during my past 3 years of trading (off and on).

I think I am having a hard time with grasping from your recent webinar that it sometimes take testing 100 to 200 trading ideas before find 1 system to move forward with live. This sounds a bit overwhelming and stare blank face in confusion to someone like me who has been watching price action only the past 2 years on the chart.

What is your suggestions or comments to the trader with the blank face thinking "I have to program and test over 100 trading ideas, before finding 1 or 2 to go live with" ?

Thanks,

 
(login for full post details)
  #252 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


goodoboy View Post
Thank you kevinkdog for the response, Good advice and simple.

Your advice is the same thing I have been thinking about over the last month or two. It is a bit of thinking of circles, but part of this trading business, I am learning is make good decisions about going forward, before losing alot of time.

You nailed my current situation with accuracy. At least I now know my where my challenges are and have some suggestions on a path forward. And most important, at least I have a path forward on the right way to properly develop and test a trading strategy. I guess I fear letting go of existing trading approach, is because that's all I know during my past 3 years of trading (off and on).

I think I am having a hard time with grasping from your recent webinar that it sometimes take testing 100 to 200 trading ideas before find 1 system to move forward with live. This sounds a bit overwhelming and stare blank face in confusion to someone like me who has been watching price action only the past 2 years on the chart.

What is your suggestions or comments to the trader with the blank face thinking "I have to program and test over 100 trading ideas, before finding 1 or 2 to go live with" ?

Thanks,

Well, I can say that most people don't believe it. Many people are stuck in this mode of "trading should be easy, just look at all the people journalling their success, or tweeting their daily profits, or smashing it day after day running a trading room..." It just CAN'T be as hard as Kevin says.

It gets depressing seeing all the people supposedly having trading success, when you are struggling. But you have to constantly remind yourself that trading is REALLY hard, and that most people fail at this.

Maybe it is not as hard for some people. But it is still hard for me, and maybe that is because I take a lot of steps to prevent mistakes, I have pretty high performance standards, and I try to be careful in developing strategies. Or maybe it is because I am doing things the hard and wrong way. I don't know.

It is hard to accept that trading is really a lot harder than you initially thought, and that maybe the approach you are doing now (whatever approach that may be) is likely never going to work. Ask yourself this: "how do I know (insert your trading approach) actually works?" Most people have no proof their approach works, just the sweet words of some "guru" that says he is not allowed to share actual trading results, or some such bs.

That realization is hard pill to swallow, as is the persistence you need to really succeed, the frustration you have to overcome, etc. You are trying to become world class at trading, and just like a champion athlete, you need a certain type of personality to succeed, even if you have the skills and some luck.

Hope this helps!

Kevin

Feel free to send me an e-mail if you want to take this conversation offline, I'll be glad to help...

Follow me on Twitter
The following 6 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #253 (permalink)
Legendary Market Wizard
Houston, TX
 
Experience: Advanced
Platform: Trading Technologies
Broker: Primary Advantage Futures. Also ED&F and Tradestation
Trading: Primarily Energy but also a little GE, GC, SI & Bitcoin
 
Posts: 3,985 since Dec 2013
Thanks: 3,288 given, 7,799 received


kevinkdog View Post
In general, based on how I develop systems, I consider it good to have return/drawdown ratios of 2.0 (meaning if you want 50% annual return, you have to endure 25% drawdowns along the way). That is the benchmark in my own trading.


SMCJB View Post
Before my October draw down I was at 1.45x, and as of Friday night I'm at 1.62x and optimistic about getting to 2.0x soon.

@gumdr0p full disclosure, the numbers I quoted last month were incorrect. My spreadsheet was incorrectly referencing minimum account balance and not the drawdown, as such the correct ratio's were lower. Thankfully after a strong week I can say that as of close Friday, after 27 weeks of trading, my return/drawdown ratio is now 1.83 based upon closed trades.

The following 2 users say Thank You to SMCJB for this post:
 
(login for full post details)
  #254 (permalink)
Legendary Market Wizard
Houston, TX
 
Experience: Advanced
Platform: Trading Technologies
Broker: Primary Advantage Futures. Also ED&F and Tradestation
Trading: Primarily Energy but also a little GE, GC, SI & Bitcoin
 
Posts: 3,985 since Dec 2013
Thanks: 3,288 given, 7,799 received

From another thread...


No BS is right. Never seen anybody do anything as open as @kevinkdog did here.
My already high opinion of Kevin, was elevated to almost atmospheric levels when I saw this last week.

The following 2 users say Thank You to SMCJB for this post:
 
(login for full post details)
  #255 (permalink)
Legendary Capt. Johnny Jameson
Fort Lauderdale
 
Experience: None
Platform: Optimus Flow, NT8. TS
Broker: CQG, Rithmic
Trading: ES
 
Devil Man's Avatar
 
Posts: 811 since Oct 2009
Thanks: 3,055 given, 1,424 received


SMCJB View Post
From another thread...


No BS is right. Never seen anybody do anything as open as @ kevinkdog did here.
My already high opinion of Kevin, was elevated to almost atmospheric levels when I saw this last week.

This is true....also can't forget that Kevin is a super nice guy on top of it!

The following 2 users say Thank You to Devil Man for this post:
 
(login for full post details)
  #256 (permalink)
Houston
 
 
Posts: 176 since Dec 2016
Thanks: 98 given, 97 received

Hello Kevin,

I am still kind of new to ATS development and study.

Is there any truth per your opinion regarding the big algo trading firms finding retail traders algo and stealing their
algo strategy from them. Something like machine learning or something? Does this apply to 1- 3 trading contracts algos?

Thanks for you input.

The following user says Thank You to goodoboy for this post:
 
(login for full post details)
  #257 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


goodoboy View Post
Hello Kevin,

I am still kind of new to ATS development and study.

Is there any truth per your opinion regarding the big algo trading firms finding retail traders algo and stealing their
algo strategy from them. Something like machine learning or something? Does this apply to 1- 3 trading contracts algos?

Thanks for you input.

Thanks for the question!!!

I think retail traders are worried about that, but I doubt big firms care about us little guys. If anything they'd spend their time trying to steal strategies from other big firms, I'd think. And 90% of people probably have worthless strats anyhow.

Really, if you are trading any algo, it probably can be easily stolen. Think of all the groups (brokers, trading platforms, exchange, phish groups, people that fix your PC) that see your orders or strategies... while they might not steal them, all those are potential weak points that could be compromised.

So I always assume my strats could be stolen, and plan accordingly...

Follow me on Twitter
The following 3 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #258 (permalink)
Site Moderator
London UK
 
Experience: Beginner
Platform: CQG
Broker: S5
Trading: Futures
 
xplorer's Avatar
 
Posts: 5,306 since Sep 2015
Thanks: 13,351 given, 12,653 received


kevinkdog View Post

Really, if you are trading any algo, it probably can be easily stolen. Think of all the groups (brokers, trading platforms, exchange, phish groups, people that fix your PC) that see your orders or strategies... while they might not steal them, all those are potential weak points that could be compromised.

So I always assume my strats could be stolen, and plan accordingly...

Hi Kevin

I've often wondered about this - I think it's reasonable to assume that any strategy written on a trading platform and that may be viewed by the platform organization (e.g. when you send your own logs and settings to support) could be stolen.

How would a broker or exchange go about doing that though? Aren't your entries and exits all they can see?


Also, this brings issues about theft of IP into the discussion. Wouldn't anyone who steals IP be liable to prosecution?

The following user says Thank You to xplorer for this post:
 
(login for full post details)
  #259 (permalink)
Luxembourg, Luxembourg
 
Experience: Advanced
Platform: TWS
Broker: Interactive Brokers
Trading: Stocks
 
Posts: 491 since May 2012
Thanks: 1,641 given, 1,149 received


kevinkdog View Post
And 90% of people probably have worthless strats anyhow.

Might be closer to 99%...

@goodoboy:
Another problem when you are looking at these type of strategies is quite simply scale. Even if someone returned 100% plus on his account trading 2-3 contracts, if the strategy can't scale with size a big institution will be wasting their time trying to reverse-engineer it. They would be much better off trying to find their own strategies that effectively use their capital.

Now, if someone had a strategy that scaled well it is another matter entirely. However, tend to be longer-term in nature (assuming you are not front-running) and a lot of them share the same characteristics. So, the pros probably already have a good idea of what you are doing...

The following user says Thank You to grausch for this post:
 
(login for full post details)
  #260 (permalink)
Luxembourg, Luxembourg
 
Experience: Advanced
Platform: TWS
Broker: Interactive Brokers
Trading: Stocks
 
Posts: 491 since May 2012
Thanks: 1,641 given, 1,149 received


xplorer View Post
Hi Kevin

I've often wondered about this - I think it's reasonable to assume that any strategy written on a trading platform and that may be viewed by the platform organization (e.g. when you send your own logs and settings to support) could be stolen.

How would a broker or exchange go about doing that though? Aren't your entries and exits all they can see?


Also, this brings issues about theft of IP into the discussion. Wouldn't anyone who steals IP be liable to prosecution?

Not Kevin, but the answer is probably still relevant.

Any reputable broker/bank would have a policy in place regarding personal trading. Of course enforcing this policy against individuals may not always be easy, but in the current environment of "information sharing", i.e. FATCA, CRS and whatever else will be dreamt up next, you never know how risky it would be trading on the side. In the absence of such a policy, and I may be mistaken, but I believe someone could trade along a broker client as long as they are not front-running.

In my previous post I mentioned scale - unless your strategy scales well, it may not represent an efficient use of the broker's time or capital to employ your strategy. If it scales well, then things may be different, but how sure are you that a) you truly have something unique or b) that your super-strategy is not a risk management nightmare that no brokerage / institution / professional would touch?

The following 2 users say Thank You to grausch for this post:
 
(login for full post details)
  #261 (permalink)
Site Moderator
London UK
 
Experience: Beginner
Platform: CQG
Broker: S5
Trading: Futures
 
xplorer's Avatar
 
Posts: 5,306 since Sep 2015
Thanks: 13,351 given, 12,653 received


grausch View Post
Not Kevin, but the answer is probably still relevant.

Any reputable broker/bank would have a policy in place regarding personal trading. Of course enforcing this policy against individuals may not always be easy, but in the current environment of "information sharing", i.e. FATCA, CRS and whatever else will be dreamt up next, you never know how risky it would be trading on the side. In the absence of such a policy, and I may be mistaken, but I believe someone could trade along a broker client as long as they are not front-running.

In my previous post I mentioned scale - unless your strategy scales well, it may not represent an efficient use of the broker's time or capital to employ your strategy. If it scales well, then things may be different, but how sure are you that a) you truly have something unique or b) that your super-strategy is not a risk management nightmare that no brokerage / institution / professional would touch?

Thanks grausch - regarding personal trading I suspect it's something that can be sidestepped - e.g. I could simply open up an account in my spouse's name.

As for scale, it's true that one way to go is to scale up, but I've seen presentations that illustrate how some algos can operate in 5-lot trades and rake up hundreds of k by the end of the day, so there's that as well to consider.

Finally, I wish I had a fully automated, unique super-strategy. I can only dream of it today


But I still enjoy talking about these issues and understanding more of the risks of IP theft, regulatory side and how people go about circumventing that of course

The following 2 users say Thank You to xplorer for this post:
 
(login for full post details)
  #262 (permalink)
Luxembourg, Luxembourg
 
Experience: Advanced
Platform: TWS
Broker: Interactive Brokers
Trading: Stocks
 
Posts: 491 since May 2012
Thanks: 1,641 given, 1,149 received


xplorer View Post
Thanks grausch - regarding personal trading I suspect it's something that can be sidestepped - e.g. I could simply open up an account in my spouse's name.

As for scale, it's true that one way to go is to scale up, but I've seen presentations that illustrate how some algos can operate in 5-lot trades and rake up hundreds of k by the end of the day, so there's that as well to consider.

Finally, I wish I had a fully automated, unique super-strategy. I can only dream of it today


But I still enjoy talking about these issues and understanding more of the risks of IP theft, regulatory side and how people go about circumventing that of course

Personal trading can be sidestepped, but trading in your spouse's name might not be smart. I may be mistaken, but I believe I read about an insider trading case where the insider tried it and got busted.

Perhaps there are algos trading with 5-lot trades, but you still need the market to move sufficiently to generate those profits. If someone uses HFT to legally front-run other traders, then you can assume that you can't operate at that level since you will never get better IT infrastructure than the top dogs.

Not sure if it is possible to make that amount of money trading 5 lots if you don't have that type of edge...

Sometimes I think that people are too concerned that brokers will steal their strategies. Most strategies I have seen aren't worth anything once they get properly tested or had been through a couple of market cycles. Brokers know this and see accounts blow up more often than you'd think - why do you think buy and hold is encouraged? It might not lead to riches, but it is very tough to blow up an unleveraged account holding shares.

The discussion definitely is interesting, but yeah, someone will always find a loophole if they want your strategy and good luck proving IP theft in court...at least if you follow Kevin's method, you will be re-optimising occasionally so whoever copied your method might be in for a rude awakening sometime in the future...

The following 3 users say Thank You to grausch for this post:
 
(login for full post details)
  #263 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


xplorer View Post
Hi Kevin

I've often wondered about this - I think it's reasonable to assume that any strategy written on a trading platform and that may be viewed by the platform organization (e.g. when you send your own logs and settings to support) could be stolen.

How would a broker or exchange go about doing that though? Aren't your entries and exits all they can see?


Also, this brings issues about theft of IP into the discussion. Wouldn't anyone who steals IP be liable to prosecution?


Anyone who sees your entries and exits could likely reverse engineer it.

Prosecution - I will be shocked if I ever see that happen!

As an aside, I had a friend who worked backoffice at brokerage. He could see everyone's account. His idea was to take a group of those traders, and then see their signals and act on it. BUT, he was going to do the opposite of thier trading, because almost all accounts lose money!!!!

He never did this, though.

Follow me on Twitter
The following 3 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #264 (permalink)
Site Moderator
London UK
 
Experience: Beginner
Platform: CQG
Broker: S5
Trading: Futures
 
xplorer's Avatar
 
Posts: 5,306 since Sep 2015
Thanks: 13,351 given, 12,653 received


kevinkdog View Post
Anyone who sees your entries and exits could likely reverse engineer it.

Prosecution - I will be shocked if I ever see that happen!

As an aside, I had a friend who worked backoffice at brokerage. He could see everyone's account. His idea was to take a group of those traders, and then see their signals and act on it. BUT, he was going to do the opposite of thier trading, because almost all accounts lose money!!!!

He never did this, though.

Thanks Kevin - but I still wonder: how could they reverse engineer it?

I mean: let's say for argument's sake my approach is based on a certain pattern occurring on a 7-minute Kagi bar which has a number of conditions taking place.

Barring the platform provider which could have arguably access to my settings, the broker or exchange will not know how my signals are generated, will they?

They won't know whether I'm trading off an hourly bar, volume bar or range bar and what's triggering my signals, right?

The following 2 users say Thank You to xplorer for this post:
 
(login for full post details)
  #265 (permalink)
Legendary Market Wizard
Houston, TX
 
Experience: Advanced
Platform: Trading Technologies
Broker: Primary Advantage Futures. Also ED&F and Tradestation
Trading: Primarily Energy but also a little GE, GC, SI & Bitcoin
 
Posts: 3,985 since Dec 2013
Thanks: 3,288 given, 7,799 received


kevinkdog View Post
As an aside, I had a friend who worked backoffice at brokerage. He could see everyone's account. His idea was to take a group of those traders, and then see their signals and act on it. BUT, he was going to do the opposite of thier trading, because almost all accounts lose money!!!!

That's what many/most forex shops do. Take the other side of the customer

The following 4 users say Thank You to SMCJB for this post:
 
(login for full post details)
  #266 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


xplorer View Post
Thanks Kevin - but I still wonder: how could they reverse engineer it?

I mean: let's say for argument's sake my approach is based on a certain pattern occurring on a 7-minute Kagi bar which has a number of conditions taking place.

Barring the platform provider which could have arguably access to my settings, the broker or exchange will not know how my signals are generated, will they?

They won't know whether I'm trading off an hourly bar, volume bar or range bar and what's triggering my signals, right?

The could probably come close to what you are doing, but they've never get your rules exactly. They'd have to have some deep pockets for a project like that though...

Follow me on Twitter
The following 3 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #267 (permalink)
Houston
 
 
Posts: 176 since Dec 2016
Thanks: 98 given, 97 received


kevinkdog View Post
Thanks for the question!!!

I think retail traders are worried about that, but I doubt big firms care about us little guys. If anything they'd spend their time trying to steal strategies from other big firms, I'd think. And 90% of people probably have worthless strats anyhow.

Really, if you are trading any algo, it probably can be easily stolen. Think of all the groups (brokers, trading platforms, exchange, phish groups, people that fix your PC) that see your orders or strategies... while they might not steal them, all those are potential weak points that could be compromised.

So I always assume my strats could be stolen, and plan accordingly...

Thanks Kevin,

So protection of strat is just another part of the learning curve I see. I will be very upset I do all this work to find a potential profitable strat and someone steals it.

Thanks

The following user says Thank You to goodoboy for this post:
 
(login for full post details)
  #268 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


goodoboy View Post
Thanks Kevin,

So protection of strat is just another part of the learning curve I see. I will be very upset I do all this work to find a potential profitable strat and someone steals it.

Thanks

That is one (very minor) reason why I develop lots of strategies. They could be stolen (highly unlikely), stop working (much more likely) or maybe have been junk to begin with (it happens!).

I have given away quite a few strategies - ones with backtest and real time profitably - and I bet 90% of people never even try to trade them...

So, I'd put "worrying about stolen strategy" way low on your priority list...

Follow me on Twitter
The following 3 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #269 (permalink)
Germany
 
Experience: Intermediate
Platform: Other
Trading: ES, YM, 6E
 
Posts: 2,668 since Feb 2013
Thanks: 5,099 given, 6,555 received

As Richard Dennis put it regarding The Turtles:

“I always say that you could publish my trading rules in the newspaper and no one would follow them.
The key is consistency and discipline. Almost anybody can make up a list of rules that are 80% as good
as what we taught our people. What they couldn’t do is give them the confidence to stick to those rules
even when things are going bad.”

In that sense, having the choice among many options like @kevinkdog, following the rules, and having
a sound understanding of what to expect in prosperity and adversity is much more important than
hiding or obfuscating systems.

The following 4 users say Thank You to choke35 for this post:
 
(login for full post details)
  #270 (permalink)
Houston
 
 
Posts: 176 since Dec 2016
Thanks: 98 given, 97 received


choke35 View Post
As Richard Dennis put it regarding The Turtles:

“I always say that you could publish my trading rules in the newspaper and no one would follow them.
The key is consistency and discipline. Almost anybody can make up a list of rules that are 80% as good
as what we taught our people. What they couldn’t do is give them the confidence to stick to those rules
even when things are going bad.”

In that sense, having the choice among many options like @kevinkdog, following the rules, and having
a sound understanding of what to expect in prosperity and adversity is much more important than
hiding or obfuscating systems.

Thanks choke35 and Kevin,

You are right about that discipline part. It whip me good when manually trading.

Yes, you are correct. At my early stage of strat development i have wayyyy BIGGER challenges to resolve then worry about someone stealing my strat. lol, wayy bigger challenges. I first have to get atleast one to work and no more red. lol

Thanks

The following 2 users say Thank You to goodoboy for this post:
 
(login for full post details)
  #271 (permalink)
Luxembourg, Luxembourg
 
Experience: Advanced
Platform: TWS
Broker: Interactive Brokers
Trading: Stocks
 
Posts: 491 since May 2012
Thanks: 1,641 given, 1,149 received


kevinkdog View Post
As an aside, I had a friend who worked backoffice at brokerage. He could see everyone's account. His idea was to take a group of those traders, and then see their signals and act on it. BUT, he was going to do the opposite of thier trading, because almost all accounts lose money!!!!

I know of a similar story. I had friends working at an institution when a known hot-shot trader opened an account with them. He was known to have made a lot of money for some of his clients and there was a lot of competition for his services. In any case he opened an account with this institution to trade his personal account.

The guys at the trading desk all executed his orders, so had real time access to his trades. When they saw the trades come in, no one thought to trade alongside him as they regarded the trades too risky and stupid. Once his account was up close to 1,000% in less than a year (pyramiding into a single trend), everyone admired his guts, but everyone still considered his strategy too risky.

After that, he had a couple of losing trades and the account was only up about 500% (down approx 50% from its peak) when he closed it. Funnily enough all of the traders considered themselves right, i.e. the guy was just lucky, he was taking on too much risk, etc. So even though they had access to the data to analyse the trades and see what made him rich, none of them considered it worth their time. They all thought they were smarter...

The following 5 users say Thank You to grausch for this post:
 
(login for full post details)
  #272 (permalink)
Dubai + United Arab Emirates
 
Experience: Intermediate
Platform: Tradestation
Trading: Emini ES, Crude CL, Gold GC, Currency Futures, Nasdaq, treasuries
 
Posts: 4 since Jan 2017
Thanks: 0 given, 3 received

Hey @kevindog

Firstly, wanted to thank you for all the insightful information presented in your book. Its truly a great read.
I really liked the practical & simple step by step methodology for creating trading strategies compared to all the hi-tech overcomplicated quant stuff we come across these days

I wanted to ask you 3 things

1) Tradestation has 2 options of WFO analysis
a) Single WFA - &
b) Cluster WFA - this uses anywhere between 5 - 20(In-Sample) runs of data and applies it to anywhere between
10-30%(Out-of Sample) Data.

Does a strategy have to PASS all the combinations of Cluster analysis or just the SINGLE WFA analysis to be considered to be taken to the Next step of Monte-Carlo analysis / incubation?

2) Tradestation has added a monte-carlo feature to their WFO, is this the same as the one you recommended in your book ?


3) If the only optimisable variables in a strategy are the exits, and if the exits itself are not fixed dollar value
( except for a fixed stop loss to minimise unforseen losses) but variable exits such as trailing ATR exits, Parabolic Exits, or exit based of a bollinger band then would one need to run the to optimise these exits in a WFO ? Wouldn't that be curve fitting ?

The following user says Thank You to arjunwhabi for this post:
 
(login for full post details)
  #273 (permalink)
Dubai + United Arab Emirates
 
Experience: Intermediate
Platform: Tradestation
Trading: Emini ES, Crude CL, Gold GC, Currency Futures, Nasdaq, treasuries
 
Posts: 4 since Jan 2017
Thanks: 0 given, 3 received

attaching an img for reference in regards to question 1

 
(login for full post details)
  #274 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


arjunwhabi View Post
Hey @kevindog

Firstly, wanted to thank you for all the insightful information presented in your book. Its truly a great read.
I really liked the practical & simple step by step methodology for creating trading strategies compared to all the hi-tech overcomplicated quant stuff we come across these days

I wanted to ask you 3 things

1) Tradestation has 2 options of WFO analysis
a) Single WFA - &
b) Cluster WFA - this uses anywhere between 5 - 20(In-Sample) runs of data and applies it to anywhere between
10-30%(Out-of Sample) Data.

Does a strategy have to PASS all the combinations of Cluster analysis or just the SINGLE WFA analysis to be considered to be taken to the Next step of Monte-Carlo analysis / incubation?

2) Tradestation has added a monte-carlo feature to their WFO, is this the same as the one you recommended in your book ?


3) If the only optimisable variables in a strategy are the exits, and if the exits itself are not fixed dollar value
( except for a fixed stop loss to minimise unforseen losses) but variable exits such as trailing ATR exits, Parabolic Exits, or exit based of a bollinger band then would one need to run the to optimise these exits in a WFO ? Wouldn't that be curve fitting ?


Thanks for the kind words, and for the questions. Here are some answers:

1. I do not use TS Walkforward tool. I use an inexpensive 3rd party piece of software that does the analysis differently

2. I use my own Monte Carlo simulator, written in Excel

3. Any time you are doing any sort of optimization you are curve fitting. I do not see your particular setup of variables being any better or worse than any other set (say with just entry parameters you optimize). The key is really to keep the # of variables low.

Sorry I could not be of more help!

Kevin

Follow me on Twitter
 
(login for full post details)
  #275 (permalink)
sweden
 
Experience: Advanced
Platform: NinjaTrader,MetaTrader
Trading: futures, FX
 
Mabi's Avatar
 
Posts: 141 since Oct 2010
Thanks: 121 given, 135 received

I use WFO more like a robustness test. If the strategy will work similar with different settings it would be a sign of robustness. However I also find that if leaving say 1 year of OOS to test the WFO strategy on 50 % of them do not improve from original and can be even worse wile the other 50 % benefited from it. I usually pick my strategies to trade from a batch that have performed recent months and find that 8 times of 10 they will perform in the near future as well so one way to do WFO could be to test it against last 1-6 months data to see if it's performance is such that you want to trade it.

The following user says Thank You to Mabi for this post:
 
(login for full post details)
  #276 (permalink)
Espoo Finland
 
Experience: Intermediate
Platform: TradingBlox
Trading: Stocks
 
Posts: 35 since Sep 2015
Thanks: 0 given, 10 received

I've read your book and it's a great piece of work. However, I am having a hard time understanding why using Walk Forward is so important. Usually what I do is optimize on my in-sample and use Monte Carlo Annual Return and Draw Down (95% confidence) to see how well my strategy works.
I then test my system on out of sample data and again use Monte Carlo so see whether I am happy with the results. Shouldn't this provide enough proof of robustness before taking it to the incubation phase?

What is the added benefit of using WFO?

The following user says Thank You to bluefightingcat for this post:
 
(login for full post details)
  #277 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


bluefightingcat View Post
I've read your book and it's a great piece of work. However, I am having a hard time understanding why using Walk Forward is so important. Usually what I do is optimize on my in-sample and use Monte Carlo Annual Return and Draw Down (95% confidence) to see how well my strategy works.
I then test my system on out of sample data and again use Monte Carlo so see whether I am happy with the results. Shouldn't this provide enough proof of robustness before taking it to the incubation phase?

What is the added benefit of using WFO?

Thanks for the kind words about the book.

Regarding walkforward, if you use a different process and verify it works well with real money, I say stick to it. Next month, I am hanging out with 3 great trader friends of mine in New York, and I'm the only one who uses walkforward. So, you definitely don't need it to succeed, but it is what I use.

That being said, here is why I like walkforward compared to traditional out of sample testing. For me, it is about maximizing the amount of out of sample results:

Traditional out of sample 80/20, Test on 10 years of data >>> optimize first 8 years, last 2 years is out of sample

Walkforward, Test on same 10 years of data, with 2 year IN period >>> 8 years out of sample performance.

So, over the same data, I get 4x the amount of out of sample data with walkforward.

Hope this helps!

Follow me on Twitter
The following user says Thank You to kevinkdog for this post:
 
(login for full post details)
  #278 (permalink)
Espoo Finland
 
Experience: Intermediate
Platform: TradingBlox
Trading: Stocks
 
Posts: 35 since Sep 2015
Thanks: 0 given, 10 received


kevinkdog View Post
Thanks for the kind words about the book.

Regarding walkforward, if you use a different process and verify it works well with real money, I say stick to it. Next month, I am hanging out with 3 great trader friends of mine in New York, and I'm the only one who uses walkforward. So, you definitely don't need it to succeed, but it is what I use.

That being said, here is why I like walkforward compared to traditional out of sample testing. For me, it is about maximizing the amount of out of sample results:

Traditional out of sample 80/20, Test on 10 years of data >>> optimize first 8 years, last 2 years is out of sample

Walkforward, Test on same 10 years of data, with 2 year IN period >>> 8 years out of sample performance.

So, over the same data, I get 4x the amount of out of sample data with walkforward.

Hope this helps!

Thanks for the reply. I got mixed feelings about WFO. I want it to work but at the same time, I'm worried it creates another layer of curve fitting possibilities and potential mistakes.

The following user says Thank You to bluefightingcat for this post:
 
(login for full post details)
  #279 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


bluefightingcat View Post
Thanks for the reply. I got mixed feelings about WFO. I want it to work but at the same time, I'm worried it creates another layer of curve fitting possibilities and potential mistakes.

Understood. If you do walkforward wrong, it can easily be curvefit. Many common software packages allow you to curvefit walkforward, with certain settings/features...

Follow me on Twitter
The following user says Thank You to kevinkdog for this post:
 
(login for full post details)
  #280 (permalink)
Legendary Market Wizard
Houston, TX
 
Experience: Advanced
Platform: Trading Technologies
Broker: Primary Advantage Futures. Also ED&F and Tradestation
Trading: Primarily Energy but also a little GE, GC, SI & Bitcoin
 
Posts: 3,985 since Dec 2013
Thanks: 3,288 given, 7,799 received

Walkforward (the way Kevin teaches it) is the bane of my existance, but also probably a life saver. I have so many things that look good at first but never can get past walkforward. That tells me they wouldn't work in real life either.


kevinkdog View Post
If you do walkforward wrong, it can easily be curvefit. Many common software packages allow you to curvefit walkforward, with certain settings/features...

Do you have any examples (settings/features not packages) where this is the case. If done correctly I can't see how your walkforwards could be increasing curve fitting.

 
(login for full post details)
  #281 (permalink)
Espoo Finland
 
Experience: Intermediate
Platform: TradingBlox
Trading: Stocks
 
Posts: 35 since Sep 2015
Thanks: 0 given, 10 received


SMCJB View Post
Walkforward (the way Kevin teaches it) is the bane of my existance, but also probably a life saver. I have so many things that look good at first but never can get past walkforward. That tells me they wouldn't work in real life either.

Do you have any examples (settings/features not packages) where this is the case. If done correctly I can't see how your walkforwards could be increasing curve fitting.

Well you have to choose "parameters" for Walk Forward e.g. length of in-sample vs length of out-sample. Which measure of goodness to use. It's easily possible to start "optimizing" the walk forward process.

Kevin: Do you have more information about your WAlk-Forward process and the practicalities related to it. Maybe a webinar or something?

The following user says Thank You to bluefightingcat for this post:
 
(login for full post details)
  #282 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


SMCJB View Post
Walkforward (the way Kevin teaches it) is the bane of my existance, but also probably a life saver. I have so many things that look good at first but never can get past walkforward. That tells me they wouldn't work in real life either.

Do you have any examples (settings/features not packages) where this is the case. If done correctly I can't see how your walkforwards could be increasing curve fitting.


I would say Cluster Analysis feature of some platforms could be curvefitting.

Follow me on Twitter
 
(login for full post details)
  #283 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


bluefightingcat View Post
Well you have to choose "parameters" for Walk Forward e.g. length of in-sample vs length of out-sample. Which measure of goodness to use. It's easily possible to start "optimizing" the walk forward process.

Kevin: Do you have more information about your WAlk-Forward process and the practicalities related to it. Maybe a webinar or something?


Yes, but only available to students...

Follow me on Twitter
 
(login for full post details)
  #284 (permalink)
Legendary Market Wizard
Houston, TX
 
Experience: Advanced
Platform: Trading Technologies
Broker: Primary Advantage Futures. Also ED&F and Tradestation
Trading: Primarily Energy but also a little GE, GC, SI & Bitcoin
 
Posts: 3,985 since Dec 2013
Thanks: 3,288 given, 7,799 received


bluefightingcat View Post
Well you have to choose "parameters" for Walk Forward e.g. length of in-sample vs length of out-sample. Which measure of goodness to use. It's easily possible to start "optimizing" the walk forward process.

Ahh okay. Yes I agree you can optimize the walkforward itself, different is/os periods, different start dates etc etc and that would obviously could lead to over fitting, which is why you shouldn't do it.


kevinkdog View Post
I would say Cluster Analysis feature of some platforms could be curvefitting.

Thank's Kevin that's interesting. As you know I've looked at Cluster Analysis, and would say in that 4 out of 5 cases my cluster analysis produces better/more stable results. My clustering is just 'average gross profit of nearest neighbors' but maybe that is the exact type of overfitting you mean. I've had so few systems pass either walkforward test though it's difficult to analyze the effect of clustering on my results.

Off topic - for many years the Texans were called Denver South. After last night I'm not sure whether we should be Cleveland South or whether you should be Houston North!

 
(login for full post details)
  #285 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


SMCJB View Post
Ahh okay. Yes I agree you can optimize the walkforward itself, different is/os periods, different start dates etc etc and that would obviously could lead to over fitting, which is why you shouldn't do it.


Thank's Kevin that's interesting. As you know I've looked at Cluster Analysis, and would say in that 4 out of 5 cases my cluster analysis produces better/more stable results. My clustering is just 'average gross profit of nearest neighbors' but maybe that is the exact type of overfitting you mean. I've had so few systems pass either walkforward test though it's difficult to analyze the effect of clustering on my results.

Off topic - for many years the Texans were called Denver South. After last night I'm not sure whether we should be Cleveland South or whether you should be Houston North!

Pretty soon, the Browns will have all the Texans picks in future drafts. But it does not matter, the Browns would screw up a draft even if they had every single pick!

I think there are ways to do Cluster analysis correctly, and ways to just curve fit with it. In any analysis/testing, I always like to see as much performance as possible with unseen data. That to me is the key.

Follow me on Twitter
The following user says Thank You to kevinkdog for this post:
 
(login for full post details)
  #286 (permalink)
San Diego, USA
 
Experience: Intermediate
Platform: MC
Trading: All
 
Posts: 48 since Aug 2016
Thanks: 7 given, 14 received

Kevin, which system would you say is more robust - the one that uses no variables (or in other words the variable is fixed and is not wf) or a system where you wf a single variable after a certain time frame? Assume here that systems are built in the same manner where IS period is all data except for the past 2 years. I am asking this question as you come across both systems but not sure which one you should strive for as logic behind both of them is usually different.

The following user says Thank You to alko for this post:
 
(login for full post details)
  #287 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


alko View Post
Kevin, which system would you say is more robust - the one that uses no variables (or in other words the variable is fixed and is not wf) or a system where you wf a single variable after a certain time frame? Assume here that systems are built in the same manner where IS period is all data except for the past 2 years. I am asking this question as you come across both systems but not sure which one you should strive for as logic behind both of them is usually different.

Really, either one could be bad, or either one could be good. It all depends HOW it was developed. For example, using no variables (where you fix the variable value) can be nice, but not if it was derived after running an optimization, then realizing you could "fix" it to a set value. Similarly, you can screw up the wf approach it multiple ways (cluster analysis when done incorrectly is just one way to mess it up).

Ultimately, no matter how you do it, live (future) data is the best judge of which is better.

Not the answer you hoped for, but I hope it helps...

Kevin

Follow me on Twitter
The following 2 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #288 (permalink)
sweden
 
Experience: Advanced
Platform: NinjaTrader,MetaTrader
Trading: futures, FX
 
Mabi's Avatar
 
Posts: 141 since Oct 2010
Thanks: 121 given, 135 received

Do you think there could be an edge from counting consecutive Loser's and Winner's in a strategies history and from that analyze and implement increased or decreased position sizing . I think the key point is to cut the extrems from a sequence
when the probability of another losing trade or another winning trade is very very weak

The following user says Thank You to Mabi for this post:
 
(login for full post details)
  #289 (permalink)
Como, Italy
 
Experience: Advanced
Platform: Tradestation, IB
Broker: Tradestation, IB
Trading: ES
 
Posts: 183 since Aug 2014
Thanks: 297 given, 312 received

I have three strategies working on ES, they did pretty good the last two years since I put them live but this year I'm really having hard times keeping them working. Overall they are still in profit YTD but numbers are very small and defenitely this is due to the low volatility. I'm trying to think which could be the events that could increase volatility, French election for example were a non event.
So I was wondering if anyother who have strategies on ES is experiencing my same difficulties...

The following user says Thank You to montanajtt for this post:
 
(login for full post details)
  #290 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


Mabi View Post
Do you think there could be an edge from counting consecutive Loser's and Winner's in a strategies history and from that analyze and implement increased or decreased position sizing . I think the key point is to cut the extrems from a sequence
when the probability of another losing trade or another winning trade is very very weak

That approach might help ONLY if your trades exhibit serial correlation.

Otherwise, it would work about as well as applying it to a random coin flip, which also has consecutive loser/winner runs. In other words, it would work only be sheer luck.

Follow me on Twitter
The following user says Thank You to kevinkdog for this post:
 
(login for full post details)
  #291 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


montanajtt View Post
I have three strategies working on ES, they did pretty good the last two years since I put them live but this year I'm really having hard times keeping them working. Overall they are still in profit YTD but numbers are very small and defenitely this is due to the low volatility. I'm trying to think which could be the events that could increase volatility, French election for example were a non event.
So I was wondering if anyother who have strategies on ES is experiencing my same difficulties...

Sure, at any given point in time, I always have some strategies doing really well, some strategies around breakeven, and some strategies doing poorly. That is why I have many strategies, in many markets, with many different styles. I want to be covered no matter what happens.

As an example, here is an ES strategy that is thriving right now. It has been hitting new equity highs (green dots) since July 2016... but I also have ES systems that aren;t doing well now, but are still within historical bounds...


Follow me on Twitter
The following 2 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #292 (permalink)
Como, Italy
 
Experience: Advanced
Platform: Tradestation, IB
Broker: Tradestation, IB
Trading: ES
 
Posts: 183 since Aug 2014
Thanks: 297 given, 312 received

Hi Kevin,
thank you for your reply, yes I know the key is diversification but I never been able to develop good strategies on any other futures then index...maybe because I understand better what I should do with index than maybe with oil or gas or wheat.

You are really good at being so well diversified, I know you have maybe 2/300 or more strategies and that is a goal I will never reach, tryed hard for years, developed thousands of strats on every symbol but very few survived the incubation period and none the real money so at the end the only profitable ended up to be those on the index.

It's not like my strats on ES are loosing money, they actually are profitable YTD but with this level of volatility trades are much less and much random. Basically I'm not concerned by results but by the fact the strategies are trading a way different market then the one they were developed for. You find below the equity curve of one of my strats.



But I know...at the end I'm only concerned because unlike you I'm not diversified enough

The following user says Thank You to montanajtt for this post:
 
(login for full post details)
  #293 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


montanajtt View Post
Hi Kevin,
thank you for your reply, yes I know the key is diversification but I never been able to develop good strategies on any other futures then index...maybe because I understand better what I should do with index than maybe with oil or gas or wheat.

You are really good at being so well diversified, I know you have maybe 2/300 or more strategies and that is a goal I will never reach, tryed hard for years, developed thousands of strats on every symbol but very few survived the incubation period and none the real money so at the end the only profitable ended up to be those on the index.

It's not like my strats on ES are loosing money, they actually are profitable YTD but with this level of volatility trades are much less and much random. Basically I'm not concerned by results but by the fact the strategies are trading a way different market then the one they were developed for. You find below the equity curve of one of my strats.



But I know...at the end I'm only concerned because unlike you I'm not diversified enough

With an equity curve like that, I would not worry about some underperformance, unless it looks dramatically unlike previous flat/down periods.

That is a nice equity curve, how much of it is live trading?

Follow me on Twitter
The following user says Thank You to kevinkdog for this post:
 
(login for full post details)
  #294 (permalink)
Como, Italy
 
Experience: Advanced
Platform: Tradestation, IB
Broker: Tradestation, IB
Trading: ES
 
Posts: 183 since Aug 2014
Thanks: 297 given, 312 received


kevinkdog View Post

That is a nice equity curve, how much of it is live trading?

Thank you, said by you it means a lot! This one is real money since March 2016 and sim since October 2015. Unfortunately it's not a so good system to run with the volatility we are experiencing since December. I have a strategy working on Nasdaq that usually traded 5/6 times a month and didn't make a trade this year yet...go figure! I guess until we go for new highs it can only go worse.

The following user says Thank You to montanajtt for this post:
 
(login for full post details)
  #295 (permalink)
Espoo Finland
 
Experience: Intermediate
Platform: TradingBlox
Trading: Stocks
 
Posts: 35 since Sep 2015
Thanks: 0 given, 10 received

I've been inspired by your book and our discussions in this forum to give WFA a try. I think I got a decent process in place but I wanted to get your opinion of whether this is viable. I am working with 15min Futures with data from 2009 until the end of 2016.

Step 1: Use data from 2009-2014 to optimise my strategy for the specific market with the aim of getting 10k per year per contract.
Step 2: Check to see whether it's still valid with out of sample data using 2015-2016.
Step 3: Optimize WF process using 2009 data (e.g. in sample/out sample lengths and ratios, and parameter sets to be stepped during WF).
Step 4: Run the WF from 2010-2016.
Step 5: Start Incubation period by live trading 1 contract.
Step 6: Gradually add contracts over next few months if continues to be successful.

Of course, with each step, you don't move to the next step unless the current step is successful.
What do you think?

The following 2 users say Thank You to bluefightingcat for this post:
 
(login for full post details)
  #296 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


bluefightingcat View Post
I've been inspired by your book and our discussions in this forum to give WFA a try. I think I got a decent process in place but I wanted to get your opinion of whether this is viable. I am working with 15min Futures with data from 2009 until the end of 2016.

Step 1: Use data from 2009-2014 to optimise my strategy for the specific market with the aim of getting 10k per year per contract.
Step 2: Check to see whether it's still valid with out of sample data using 2015-2016.
Step 3: Optimize WF process using 2009 data (e.g. in sample/out sample lengths and ratios, and parameter sets to be stepped during WF).
Step 4: Run the WF from 2010-2016.
Step 5: Start Incubation period by live trading 1 contract.
Step 6: Gradually add contracts over next few months if continues to be successful.

Of course, with each step, you don't move to the next step unless the current step is successful.
What do you think?

Thanks for the question. This is different than what I do, and I've never done it the way you are proposing, so I can't say for sure how good it is. But, it very well could work out well - you just have to test it with a bunch of strategies, and see how it does.

I would NOT recommend step 5, unless you have money to burn. Trading live right after developing the strategy is generally not a good idea. The whole idea with incubation is that you want to see if the strategy falls apart in real time, without having actual money on the line. Of course, there is an opportunity cost to this (watching a good performing strategy live, but not trading it with real money), but for most people, waiting to see if walkforward performance continues is generally a good idea.

Good Luck, and keep everyone informed how it goes!

Follow me on Twitter
 
(login for full post details)
  #297 (permalink)
Espoo Finland
 
Experience: Intermediate
Platform: TradingBlox
Trading: Stocks
 
Posts: 35 since Sep 2015
Thanks: 0 given, 10 received


Quoting 
I would NOT recommend step 5, unless you have money to burn.

The reason I choose to do incubation with real money is because you get a better idea about things like slippage and how orders fill. A paper account will never be fully accurate in that sense. I learned this the hard way in the past with a strategy looking good on paper but that would fall apart because of harder slippage during live trading. Of course these days, in my backtests, I tend to put a little extra slippage and commission than a little too little.

But thanks for your advice. I will definitely have a re-think about the live incubation part.

The following user says Thank You to bluefightingcat for this post:
 
(login for full post details)
  #298 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


bluefightingcat View Post
The reason I choose to do incubation with real money is because you get a better idea about things like slippage and how orders fill. A paper account will never be fully accurate in that sense. I learned this the hard way in the past with a strategy looking good on paper but that would fall apart because of harder slippage during live trading. Of course these days, in my backtests, I tend to put a little extra slippage and commission than a little too little.

But thanks for your advice. I will definitely have a re-think about the live incubation part.

Understood, I have done that before, once when I was trading an NG strategy around weekly report time. I had no idea what slippage would be, since everyone pulls their orders right at the report time.

Turns out I was underestimating slippage, and even though the strategy was still profitable, it wasn't great on a reward/risk basis, so I stopped trading it.

Not sure how you are doing orders, etc, but usually I use market orders to get in and out, and normally using 1-2 x the bid ask spread is a good estimate of slippage.

Follow me on Twitter
 
(login for full post details)
  #299 (permalink)
Espoo Finland
 
Experience: Intermediate
Platform: TradingBlox
Trading: Stocks
 
Posts: 35 since Sep 2015
Thanks: 0 given, 10 received

In your book you touch on position sizing. I was particularly interested in the position sizing method when trading several markets at the same time and taking into account correlation.

What kind of software do you use to do the analysis?

 
(login for full post details)
  #300 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


bluefightingcat View Post
In your book you touch on position sizing. I was particularly interested in the position sizing method when trading several markets at the same time and taking into account correlation.

What kind of software do you use to do the analysis?


Thanks for the question. And thanks for reading my book!


I use Excel for all my position sizing analysis. I've created tons of different spreadsheets over the years doing all sorts of crazy stuff. But nowadays I tend to keep things simple, still using Excel, but trying not to overthink the whole thing (which usually only makes historical testing look better!).

Follow me on Twitter

Closed Thread

futures io Trading Community Trading Reviews and Vendors > KJ Trading Systems Kevin Davey - Ask Me Anything (AMA)


Last Updated on July 5, 2019


Upcoming Webinars and Events
 

NinjaTrader Indicator Challenge!

Ongoing
 

Battlestations! Show us your trading desk - $1,500 in prizes!

March
 

Importance of Finding Your Own Way w/Adam Grimes

Elite only
 

Journal Challenge w/Jigsaw

April
     



Copyright © 2021 by futures io, s.a., Av Ricardo J. Alfaro, Century Tower, Panama, +507 833-9432, info@futures.io
All information is for educational use only and is not investment advice.
There is a substantial risk of loss in trading commodity futures, stocks, options and foreign exchange products. Past performance is not indicative of future results.
no new posts