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)
  #101 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


FABRICATORX View Post
Thank you Kevin @kevinkdog for your time.

I am very novice. I have a managed acct with an algo trader (5 years now), and have been interested for some time. Now I have the career that gives me the time to make this a hobby. The owner of the algo shop has been a mentor for me, so while my learning has been very succinct (cutting out BS) I am still in the early stages.

I have a background in cognitive psychology (hobby, not professionally) and know that we can't be trusted to be consistent, so algo has been my focus.

I'm in the reading phase, and have been devouring your blog and others. I have most of the books you mentioned on your site on my list, but haven't pulled the trigger on yours yet. Those 1 star reviews have quite the effect, being that we're innately risk averse lol. After speaking with you, however, I will download soon.

I will look at the SF program in the next year.

Thanks for being awesome. You're a family man and I'm proud of you for keeping your family in focus. Good work

Thanks for the kind words. If you are happy with the managed acct, and the person running it wants to be your mentor, I would pursue that route big time. Nothing beats someone to guide you through the trading morass...

On another note, glad you decided to ignore the few 1 star reviews of my book. There are people out there who would give 1 star to a book that had $50 bills in between each page. These folks probably also give 1 stars to folks like Pardo and Kauffman, and those guys are legends...

Follow me on Twitter
The following 3 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #102 (permalink)
PTA, Gauteng
 
Experience: Advanced
Platform: Self built + Sierra + TWS
Trading: Stocks and Options
 
DarkPoolTrading's Avatar
 
Posts: 1,036 since May 2012
Thanks: 1,244 given, 1,320 received


kevinkdog View Post
On another note, glad you decided to ignore the few 1 star reviews of my book. There are people out there who would give 1 star to a book that had $50 bills in between each page. These folks probably also give 1 stars to folks like Pardo and Kauffman, and those guys are legends...

I can certainly attest to Kevin's book being excellent. I purchased it two weeks ago and finished it in one weekend, I just didn't want to put it down (while taking lots of notes). I will certainly read it again sometime.

The only thing I disagree with is Monte Carlo analysis. However that has nothing to do with the quality of Kevin's book. It is just me not agreeing with the value of Monte Carlo. Kevin, i've been meaning to pop you a pm sometime to hear your thoughts on why I do not think it has any real value. I would like to hear your take after hearing my reasoning.


kevinkdog View Post
By the way, if you order my book, shoot me an e-mail with the order confirmation. I'll give you 5 bonus reports free, as part of the 1st anniversary of the book release.

Kevin, does this just apply to new purchases going forward,...or could I shoot you an email with my order confirmation from a couple weeks ago?

Diversification is the only free lunch
Follow me on Twitter
The following 2 users say Thank You to DarkPoolTrading for this post:
 
(login for full post details)
  #103 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


DarkPoolTrading View Post
I can certainly attest to Kevin's book being excellent. I purchased it two weeks ago and finished it in one weekend, I just didn't want to put it down (while taking lots of notes). I will certainly read it again sometime.

The only thing I disagree with is Monte Carlo analysis. However that has nothing to do with the quality of Kevin's book. It is just me not agreeing with the value of Monte Carlo. Kevin, i've been meaning to pop you a pm sometime to hear your thoughts on why I do not think it has any real value. I would like to hear your take after hearing my reasoning.



Kevin, does this just apply to new purchases going forward,...or could I shoot you an email with my order confirmation from a couple weeks ago?

Check your PM.

Thanks!

Follow me on Twitter
 
(login for full post details)
  #104 (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


DarkPoolTrading View Post
I can certainly attest to Kevin's book being excellent. I purchased it two weeks ago and finished it in one weekend, I just didn't want to put it down (while taking lots of notes). I will certainly read it again sometime.

The only thing I disagree with is Monte Carlo analysis. However that has nothing to do with the quality of Kevin's book. It is just me not agreeing with the value of Monte Carlo. Kevin, i've been meaning to pop you a pm sometime to hear your thoughts on why I do not think it has any real value. I would like to hear your take after hearing my reasoning.



Kevin, does this just apply to new purchases going forward,...or could I shoot you an email with my order confirmation from a couple weeks ago?

@DarkPoolTrading I'm also curious on your take on Monte Carlo Sim. As we know, the pragmatic approach is to view one concept from multiple very different viewpoints.

Perhaps another thread where it can be debated? @kevinkdog

-Jimmy
 
(login for full post details)
  #105 (permalink)
NGP MS India
 
 
Posts: 16 since May 2015
Thanks: 26 given, 2 received

hi kevin!

i am using ur monte carlo sheet. Thanks for it.

have some query on the same.

do monte carlo sim results fools us? or backtesting.

i did backtesting with few years data, hiding some data , did monte carlo but results where bad.

incubation was best but when i repeated the process with walk forward,incubation and again back testing with unseen data it was good but not in monte carlo.

only one positives i found with monte carlo,it can predict or advice best capital amt to be employed with less ruin and dd.

which data is correct which is fooling us?

thanks

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


haraj View Post
hi kevin!

i am using ur monte carlo sheet. Thanks for it.

have some query on the same.

do monte carlo sim results fools us? or backtesting.

i did backtesting with few years data, hiding some data , did monte carlo but results where bad.

incubation was best but when i repeated the process with walk forward,incubation and again back testing with unseen data it was good but not in monte carlo.

only one positives i found with monte carlo,it can predict or advice best capital amt to be employed with less ruin and dd.

which data is correct which is fooling us?

thanks


If you build your system incorrectly, and use data from it in Monte Carlo, then the results will be bogus.

If you build your system correctly, especially with walkforward analysis (again, done correctly), then my experience is that Monte Carlo can be a big benefit.

But if you believe your results are suspect before MC, I certainly would not use them.

Follow me on Twitter
The following 2 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #107 (permalink)
NGP MS India
 
 
Posts: 16 since May 2015
Thanks: 26 given, 2 received


kevinkdog View Post
If you build your system incorrectly, and use data from it in Monte Carlo, then the results will be bogus.

If you build your system correctly, especially with walk forward analysis (again, done correctly), then my experience is that Monte Carlo can be a big benefit.

But if you believe your results are suspect before MC, I certainly would not use them.

thanks kevin!

i mean i am working on strategy, its complete visual with no programming.. i did paper trade , simulation trades and is in incubation period. I have incubation data of 3 years with different market sentiments


can i directly use data from incubation to monte carlo sim!

infact i tried and results are amazing.

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


haraj View Post
thanks kevin!

i mean i am working on strategy, its complete visual with no programming.. i did paper trade , simulation trades and is in incubation period. I have incubation data of 3 years with different market sentiments


can i directly use data from incubation to monte carlo sim!

infact i tried and results are amazing.

I would say 3 years is not enough data for MC simulation, but then again, I don;t use incubation data when I run the MC (I use walkforward out of sample results). Although after having 3 years of incubation data, do you really need more confirmation of your system's performance? How much more incubation data do you need?

Follow me on Twitter
 
(login for full post details)
  #109 (permalink)
Seattle,WA
 
Experience: Advanced
Platform: NinjaTrader , Multicharts and my own system
Trading: Futures
 
Posts: 294 since Feb 2015
Thanks: 19 given, 459 received

In your book you mention testing a strategy on 10 minute bars and then varying the test by 1 minute to see how it changes the performance of the system. How do you decide how much of a performance decrease is acceptable when changing the bar timeframe by 1 minute? For example if a strategy makes 200% profit but drops to 50% would you still feel it is ok to trade?

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


Aufidius View Post
In your book you mention testing a strategy on 10 minute bars and then varying the test by 1 minute to see how it changes the performance of the system. How do you decide how much of a performance decrease is acceptable when changing the bar timeframe by 1 minute? For example if a strategy makes 200% profit but drops to 50% would you still feel it is ok to trade?

Thanks for the question. I still do this kind of testing on occasion, but nowadays I don't normally do it as part of my development process. Why not? Well, I guess I have seen too many times where a 10 minute bar creates a great strategy, but a 9 minute or even 11 minute doesn't. I have concluded that some of that performance difference could be real, since many more people are using 10 minute charts to be entering and exiting, and my strategy may have caught some of that actual price behavior.

So, I guess I am saying I would not be turned off any longer by the case you present. I would likely still find it acceptable.

What I would not do is try the system with 8, 9, 10, 11, and 12 minute bars, and then pick the best one overall. I think that is bad optimizing.

Hope this helps!

Follow me on Twitter
 
(login for full post details)
  #111 (permalink)
Houston, TX
 
Experience: Intermediate
Platform: NinjaTrader TWS Barchart
Broker: IB / IB
Trading: SPY, QQQ
 
ElChacal's Avatar
 
Posts: 408 since Nov 2014
Thanks: 470 given, 276 received

@kevinkdog how do you feel about holding a position overnight let's say on ES?
I came up with a good swing strategy on a Daily Chart so I need to place my stop a little far, let's assume 2*(ATR(20days))

I am no big fan of lower timeframes yet. If from a money management perspective makes sense, would you hold it?

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


ElChacal View Post
@kevinkdog how do you feel about holding a position overnight let's say on ES?
I came up with a good swing strategy on a Daily Chart so I need to place my stop a little far, let's assume 2*(ATR(20days))

I am no big fan of lower timeframes yet. If from a money management perspective makes sense, would you hold it?

I have no problem with overnight strategies. They are actually easier to develop than intraday. I also think the market pays a "risk premium" to those willing to take on the overnight risk.

I bet 90% of my strategies are swing type, lasting days to weeks to months.

I like intraday strats, too, but they are much harder to find...

Follow me on Twitter
The following 5 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #113 (permalink)
Houston, TX
 
Experience: Intermediate
Platform: NinjaTrader TWS Barchart
Broker: IB / IB
Trading: SPY, QQQ
 
ElChacal's Avatar
 
Posts: 408 since Nov 2014
Thanks: 470 given, 276 received

@kevinkdog it is awesome to hear it from you. Yes, my good strategies are on daily charts. I would go discretionary intraday to get a good fill.

Man you raise the bar in this forum to a whole new level.
@Big Mike thanks for this forum dude. I am on my first real trade today ever and so far it's turning out to be a great day.

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


ElChacal View Post
@kevinkdog it is awesome to hear it from you. Yes, my good strategies are on daily charts. I would go discretionary intraday to get a good fill.

Man you raise the bar in this forum to a whole new level.
@Big Mike thanks for this forum dude. I am on my first real trade today ever and so far it's turning out to be a great day.

Congrats, just remember it is a marathon, not a sprint...

Your tagline "patience my young Padawan" is definitely appropriate!!!

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


ElChacal View Post
I would go discretionary intraday to get a good fill.

I personally would not recommend this, if you are using discretion to "help" with a mechanical/rule based strategy. I think in the long run you are setting yourself up for trouble.

When I go with a rules based strategy, I follow rules 100% of the time. No discretion....

Follow me on Twitter
The following 4 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #116 (permalink)
Houston, TX
 
Experience: Intermediate
Platform: NinjaTrader TWS Barchart
Broker: IB / IB
Trading: SPY, QQQ
 
ElChacal's Avatar
 
Posts: 408 since Nov 2014
Thanks: 470 given, 276 received


kevinkdog View Post
I personally would not recommend this, if you are using discretion to "help" with a mechanical/rule based strategy. I think in the long run you are setting yourself up for trouble.

When I go with a rules based strategy, I follow rules 100% of the time. No discretion....

Thanks. I will apply this. The little detail is the daily charts I like with the stop I like are a little over the money management rules. Starting up with $11k and I would be risking more than 2-3% of my account per trade if the stop gets hit.
It is really bad to trade with scared money so I am trying this not to affect me while I hold per the plan.

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


ElChacal View Post
Thanks. I will apply this. The little detail is the daily charts I like with the stop I like are a little over the money management rules. Starting up with $11k and I would be risking more than 2-3% of my account per trade if the stop gets hit.
It is really bad to trade with scared money so I am trying this not to affect me while I hold per the plan.

This is always a tough one, since a lot of people say risk only 1-2% per trade.

The problem is exactly what you are experiencing - with a small account, this means a very tight stop. And of course very tight stops get hit more often, and you may lose that way.

In my own trading, I used to (and sometimes still do) violate the "2%" rule. But it comes at a cost - the odds of getting wiped out go up. It is a balancing act.

Just make sure whatever you do (big stop, small stop) has a long term expectancy...

Follow me on Twitter
The following user says Thank You to kevinkdog for this post:
 
(login for full post details)
  #118 (permalink)
Houston, TX
 
Experience: Intermediate
Platform: NinjaTrader TWS Barchart
Broker: IB / IB
Trading: SPY, QQQ
 
ElChacal's Avatar
 
Posts: 408 since Nov 2014
Thanks: 470 given, 276 received


kevinkdog View Post
I personally would not recommend this, if you are using discretion to "help" with a mechanical/rule based strategy. I think in the long run you are setting yourself up for trouble.

When I go with a rules based strategy, I follow rules 100% of the time. No discretion....

I realized this week that if I had gone mechanical, I would have made a lot more money and avoided bad trades (chasing).

By going discretionary any small retracement plays against my psychology big time and I just want out.

Ironically enough, I have basically ignored all the backtesting and hard work I have been doing for a year now.

I will do some more tweaks to the bot to see if I can get a better fill intraday once I get the trade signal, probably tighten the stop a little and see what happens.

Don't rush it and go with what you've already tested. That's definitely the key.

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


ElChacal View Post
I realized this week that if I had gone mechanical, I would have made a lot more money and avoided bad trades (chasing).

By going discretionary any small retracement plays against my psychology big time and I just want out.

Ironically enough, I have basically ignored all the backtesting and hard work I have been doing for a year now.

I will do some more tweaks to the bot to see if I can get a better fill intraday once I get the trade signal, probably tighten the stop a little and see what happens.

Don't rush it and go with what you've already tested. That's definitely the key.

Sounds great! This is a common problem - people run the tests, but ignore or try to overrule the results.

The other mistakes people tend to make: focusing too much on the backtest, tweaking it over and over to get better performance. It makes the backtest look better, but usually does not translate to real time performance...

Follow me on Twitter
The following 3 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #120 (permalink)
Luxembourg, Luxembourg
 
Experience: Advanced
Platform: TWS
Broker: Interactive Brokers
Trading: Stocks
 
Posts: 491 since May 2012
Thanks: 1,641 given, 1,149 received


ElChacal View Post
By going discretionary any small retracement plays against my psychology big time and I just want out.

You never really get rid of that even if you trade systematically...you can however make peace with it and accept it as part of business. Not watching the screen like a hawk tends to help with that specific issue.

The following 2 users say Thank You to grausch for this post:
 
(login for full post details)
  #121 (permalink)
Houston, TX
 
Experience: Intermediate
Platform: NinjaTrader TWS Barchart
Broker: IB / IB
Trading: SPY, QQQ
 
ElChacal's Avatar
 
Posts: 408 since Nov 2014
Thanks: 470 given, 276 received


grausch View Post
You never really get rid of that even if you trade systematically...you can however make peace with it and accept it as part of business. Not watching the screen like a hawk tends to help with that specific issue.

Man you just described my entire week. LOL

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


ElChacal View Post
Man you just described my entire week. LOL

Wish I could say that I was any different...

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


grausch View Post
You never really get rid of that even if you trade systematically...you can however make peace with it and accept it as part of business. Not watching the screen like a hawk tends to help with that specific issue.

Yes, people tend to think "oh, I'll just trade systematically, and then my emotions will be under control." I thought that too.

Unfortunately, it doesn't work that way. Emotions are still there, but they just manifest in different ways.

Maybe my experience will help...

I used to chart my equity every day. As you can imagine, all the ups and downs (thankfully more ups) made me crazy. So, the last few years, I have charted my equity only on a weekly basis. I'll admit sometimes I cheat and still calculate daily equity, but many days I only have a vague sense if I made money or lost money.

The cool thing about this is my focus is different now: not "am I making money?" but "am I trading correctly?" I can't control the money making part, but I can control the doing things correctly part, and by focusing on what I can actually influence I find myself a lot calmer and more in charge of things with this approach.

Follow me on Twitter
The following 13 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #124 (permalink)
Luxembourg, Luxembourg
 
Experience: Advanced
Platform: TWS
Broker: Interactive Brokers
Trading: Stocks
 
Posts: 491 since May 2012
Thanks: 1,641 given, 1,149 received

Kevin,

Thanks for your feedback.

I still view my P&L daily, but I really should only focus on the charts and the trades. I find that seeing the big red / green block in Interactive Brokers with my daily P&L more of a hindrance than a help.

If I just focus on my excel sheets which track my performance, I just see a % move for the month and I just feel a lot better about my trading. As long as it is positive, I don't care too much about it. Once it gets negative, I scale back my trades and once it reaches -2%, I trade tiny size (less than 1% of my portfolio invested in a stock - total exposure < 10%). At that point it is all about feeling out the market and getting my rhythm back.

However, I never found a way to effectively implement that type of position sizing in my long term systems. Seemed like they caught all the really good trades on reduced size and all the bad trades on normal size.

The following 3 users say Thank You to grausch for this post:
 
(login for full post details)
  #125 (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
Yes, people tend to think "oh, I'll just trade systematically, and then my emotions will be under control." I thought that too.

Unfortunately, it doesn't work that way. Emotions are still there, but they just manifest in different ways.



Well, I think quant trading can be much more stressing then discretionary, the only sure thing is that nothing works forever and nobody knows when that time will come for a strategy. So this add much stress, if something is performing good you expect a drawdown and if it's performing bad you start think it is broken.
The only cure is diversification, I've read in the option selling thread you have 78 strategies running. I'm very very far to be such diversified but I agree with your point. Also diversification has a cost and I think it is useful to have a yearly budget for R/D that do not impact to your performance too much.

The following 3 users say Thank You to montanajtt for this post:
 
(login for full post details)
  #126 (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

Kevin, I don't recall if this was discussed in your book.

What are the primary differences between your personal strategies, and a strategy used for World Cup trading?

Would you say they have a higher risk % and higher risk of ruin? Are they something you throw out there and say "well it will either blow up, or win 1st place".

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


FABRICATORX View Post
Kevin, I don't recall if this was discussed in your book.

What are the primary differences between your personal strategies, and a strategy used for World Cup trading?

Would you say they have a higher risk % and higher risk of ruin? Are they something you throw out there and say "well it will either blow up, or win 1st place".

They were the same strategies that I would use in "normal" trading, but with greatly reduced initial capital.

So, when I won the World Cup, I had a strategies trading 6-10 different markets. A prudent trader would have been trading such a setup with probably $30-45K. I started with $15K. Thus, my returns (and drawdowns) were probably double or more of a typical account.

The big thing to me was I had a goal (>100% return in a year), and I had to get a trading setup (strategies, account size, position sizing) in place to meet that goal. That to me was the most important part - starting with a goal.

Follow me on Twitter
The following 6 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #128 (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

Dude, the Return/DD ratio is life changing for systems development.

I was plugging away in excel, using your freemc spreadsheet, when I realized the significance of what that means.

Now I have some systems with a Ret/DD over 35.

Maximum attack with minimal pucker.

Thanks dude,

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


FABRICATORX View Post
Dude, the Return/DD ratio is life changing for systems development.

I was plugging away in excel, using your freemc spreadsheet, when I realized the significance of what that means.

Now I have some systems with a Ret/DD over 35.

Maximum attack with minimal pucker.

Thanks dude,

Over 35? WOW. I usually am happy with ratio over 2.0

Follow me on Twitter
 
(login for full post details)
  #130 (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

Dude the long-term timeframes are sooooo much better.

In theory, short term timeframes provide higher equity resolution, but I get absolutely hammered in them.

My goal was 1.5:1 lol


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


FABRICATORX View Post
Dude the long-term timeframes are sooooo much better.

In theory, short term timeframes provide higher equity resolution, but I get absolutely hammered in them.

My goal was 1.5:1 lol


Can you post a screenshot of results, or send me a copy of the spreadsheet with results? 35 sounds too good to be true.

Follow me on Twitter
The following 2 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #132 (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

Yup, I'll email it.

Hmm, I might have found something. I copy/pasted my trades, but there wasn't a trade every day, so there are some blanks.

You'll see. I'm sending two copies of different strategies.

In the meantime, I'm rebuilding the strategies to ensure I didn't fudge something here.

EDIT!

It was the blanks, guys. When entering trade results, don't leave any blanks, even if there was no trade. The monte carlo algo will stop pulling data at the blank.

On a related note, @kevinkdog is the man

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


FABRICATORX View Post
Dude, the Return/DD ratio is life changing for systems development.

The ratio was initially used by a publication called the Managed Accounts Report which was tracking CTAs. See here for some history of the MAR - MAR Ratio Definition | Investopedia.

If you are interested in some further reading on system development and some interesting thoughts by Ed Seykota, then refer to this link - https://www.seykota.com/tribe/TSP/index.htm. The System Math document (under resources) is still one of my references. Unfortunately he has not updated the TSP site in 10 years, and I don't think we will see updates any time soon.


FABRICATORX View Post
Now I have some systems with a Ret/DD over 35.

As you determined in a later post, that was actually due to an error in your code. The best CTAs with a long history tend to have MARs of about 0.5. I would regard 0.5 as exceptional for a trend-following system on daily bars. Most funds struggle to get even close to that.

Kevin seems to use 2 as a good measure for his work, therefore in order to be safe, you could consider reviewing any system with a MAR over 2 very carefully for either errors in the code, errors in your logic, or a system that has been curve fit to the dataset.

The following 4 users say Thank You to grausch for this post:
 
(login for full post details)
  #134 (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

Yes I found errors in the monte carlo, as well as the strategy itself.

I accidentally used semi-forward looking data in my code. I addressed that.

Still good strategy though

I need to incorporate slippage and commission, so I'm not sure what to pick. 2-3 ticks?

Thanks guys

PS - great link on Seykota!

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


FABRICATORX View Post
Yes I found errors in the monte carlo, as well as the strategy itself.

I accidentally used semi-forward looking data in my code. I addressed that.

Still good strategy though

I need to incorporate slippage and commission, so I'm not sure what to pick. 2-3 ticks?

Thanks guys

PS - great link on Seykota!


For YM, I'd use at least $20 per round turn per contract for slippage.

Follow me on Twitter
The following user says Thank You to kevinkdog for this post:
 
(login for full post details)
  #136 (permalink)
Milan, Italy
 
Experience: Intermediate
Platform: Amiborker
Broker: IB
Trading: stocks
 
theucreport's Avatar
 
Posts: 11 since Aug 2010
Thanks: 160 given, 11 received

I'm reading your book and I have to say that is the best I have read so far on algo trading systems.
I'm looking forward to the next one

I have three AMA questions for you:

1) For those who cannot attend your workshops, do you plan to sell video of those?
2) I know that you use Tradestation, but do you know successful traders that perform live automatic trading with Amibroker?
3) What is the minimum capital to swing trade 2-4 uncorrelated automatic strategies with e-mini futures without the risk to blow up the account (the goal).

Thanks a lot and take care!

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


theucreport View Post
I'm reading your book and I have to say that is the best I have read so far on algo trading systems.
I'm looking forward to the next one

I have three AMA questions for you:

1) For those who cannot attend your workshops, do you plan to sell video of those?
2) I know that you use Tradestation, but do you know successful traders that perform live automatic trading with Amibroker?
3) What is the minimum capital to swing trade 2-4 uncorrelated automatic strategies with e-mini futures without the risk to blow up the account (the goal).

Thanks a lot and take care!

Thanks a lot - I do appreciate it.

If you get a chance to review it on Amazon or here at futures.io (formerly BMT), I would be grateful:



To answer your questions:

1) For the workshop, traders who attend gets copies of the full recording. Plus, they can re-attend future live workshops for free. So, you have plenty of opportunity to repeat or listen again.

2) I don't personally know many Amibroker traders, but I am sure there are successful one out there. I don't know about the automation part though, and how well it works with Amibroker.

3) Account sizing is always a tough question, since it depends a lot on the trader's temperament (can you only handle 10% drawdown, or is 40% OK?). It also depends a lot on the strategies you choose to trade and how they work together (good strategies complement each other, and smooth the equity curve). I actually provide an account sizing video as part of the workshop, since it is a topic worthy of a lot of thought. Sorry I can't get more specific...

Thanks!

Follow me on Twitter
The following 2 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #138 (permalink)
hong kong
 
Experience: Intermediate
Platform: Multicharts
Trading: Future
 
Posts: 2 since Jul 2015
Thanks: 0 given, 1 received

I joined the strategy factory course in July 2015. Kevin don't just give you the correct method of testing and creating a strategy. What I think the course is most valuable is he provide 6 months post course email support. you can email him any question and you will get professional reply from a real trader. It is a must join course for everyone who want to become a successful algo trader.

The following 3 users say Thank You to dingmanhoe123 for this post:
 
(login for full post details)
  #139 (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

Hey dude - thinking about Fed days.

What has your research shown in regards to trading Fed days?

I haven't run my own studies yet, but curious to see whats out there. I'm looking at daily bar, US market stuff.

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


FABRICATORX View Post
Hey dude - thinking about Fed days.

What has your research shown in regards to trading Fed days?

I haven't run my own studies yet, but curious to see whats out there. I'm looking at daily bar, US market stuff.


I have never done any research. I test it like any other day.

If you knew exact dates and times of all historical scheduled announcements, etc, you could trade just those days or exclude just those days if you cared to. A lot of work to do it though...

Follow me on Twitter
 
(login for full post details)
  #141 (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
I have never done any research. I test it like any other day.

If you knew exact dates and times of all historical scheduled announcements, etc, you could trade just those days or exclude just those days if you cared to. A lot of work to do it though...

That's why I didn't do it yet lol.

I'll dig and see what I can find.

Jimmy

-Jimmy
 
(login for full post details)
  #142 (permalink)
Barcelona Spain
 
 
Posts: 13 since Aug 2015
Thanks: 15 given, 7 received

I would like to put a simple question, something that concerns me but it's probably quite simple and common on the day to day of sistematic trading, I suspect.

I've been designing a bunch of strategies. Most of them are real rubish from the very beginning, others don't support a quick backtest though looking good on its preliminary results, others come together with extremes drawdawn though beeing profitable most of the time (too risky for me). BUT I have a couple of them that give me good results, and I mean with good results: Good ratios: Maximum Drawdawn (Ok), Profit factor (Ok), return/DD (Ok), Walf Fordward Eff. (Ok). Great! Holy Grail! Eureka!

My concern is that those promising results are only presents for a single index. On other markets like FX, Commodities, even other indexes they simply and clearly fail no matter the parameters I use. So, what do you do with those strategies? Go ahead on that single market or just discard them because of lack of robustness?

I have the feeling to discard them despite all the sweat, blood and tears invested. I don't trust them if they just pass the exam in one index. But on that single market they are outstanding! Right now I'm passing and continue with more ideas, trying to cold down my mind and come back to those strategies later...

I'll appreciate your wise comments

The following user says Thank You to Enric66 for this post:
 
(login for full post details)
  #143 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


Enric66 View Post
I would like to put a simple question, something that concerns me but it's probably quite simple and common on the day to day of sistematic trading, I suspect.

I've been designing a bunch of strategies. Most of them are real rubish from the very beginning, others don't support a quick backtest though looking good on its preliminary results, others come together with extremes drawdawn though beeing profitable most of the time (too risky for me). BUT I have a couple of them that give me good results, and I mean with good results: Good ratios: Maximum Drawdawn (Ok), Profit factor (Ok), return/DD (Ok), Walf Fordward Eff. (Ok). Great! Holy Grail! Eureka!

My concern is that those promising results are only presents for a single index. On other markets like FX, Commodities, even other indexes they simply and clearly fail no matter the parameters I use. So, what do you do with those strategies? Go ahead on that single market or just discard them because of lack of robustness?

I have the feeling to discard them despite all the sweat, blood and tears invested. I don't trust them if they just pass the exam in one index. But on that single market they are outstanding! Right now I'm passing and continue with more ideas, trying to cold down my mind and come back to those strategies later...

I'll appreciate your wise comments


If you don't trust them, don't trade them.

You have the opinion that a strategy must work in multiple markets to be considered "robust." Maybe you should ask yourself why that has to be true. Why does a strategy that works on the ES also have to work on the Euro currency? Or, does an ES strategy have to work on the TF or NQ - and if so, how good does it have to be?

Examine your mindset about this requirement you have - that a strategy should work on multiple markets to be robust. I'm not saying it is right or wrong. And as long as you are satisfied your requirements are based on sound logic, then definitely throw away strategies that don't meet your requirements.

I hope this helps!

Follow me on Twitter
The following 5 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #144 (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

Here's something I found in my own results - I have a system that trades the US markets well, all except one.

It performs well in ES, YM, ZB, ZN. I apply any iteration of it to NQ, and it is erratic and flat. It doesn't lose, but, it doesn't win either lol.

-Jimmy
The following user says Thank You to FABRICATORX for this post:
 
(login for full post details)
  #145 (permalink)
Site Administrator
Swing Trader
Data Scientist & DevOps
Manta, Ecuador
 
Experience: Advanced
Platform: My own custom solution
Trading: Emini Futures
 
Big Mike's Avatar
 
Posts: 49,790 since Jun 2009
Thanks: 32,314 given, 97,615 received


Enric66 View Post
I would like to put a simple question, something that concerns me but it's probably quite simple and common on the day to day of sistematic trading, I suspect.

I've been designing a bunch of strategies. Most of them are real rubish from the very beginning, others don't support a quick backtest though looking good on its preliminary results, others come together with extremes drawdawn though beeing profitable most of the time (too risky for me). BUT I have a couple of them that give me good results, and I mean with good results: Good ratios: Maximum Drawdawn (Ok), Profit factor (Ok), return/DD (Ok), Walf Fordward Eff. (Ok). Great! Holy Grail! Eureka!

My concern is that those promising results are only presents for a single index. On other markets like FX, Commodities, even other indexes they simply and clearly fail no matter the parameters I use. So, what do you do with those strategies? Go ahead on that single market or just discard them because of lack of robustness?

I have the feeling to discard them despite all the sweat, blood and tears invested. I don't trust them if they just pass the exam in one index. But on that single market they are outstanding! Right now I'm passing and continue with more ideas, trying to cold down my mind and come back to those strategies later...

I'll appreciate your wise comments

Sorry for stepping in with my opinion in Kevin's AMA, but if a strategy fails to perform similarly on a highly correlated instrument, then it's a sure sign of curve fitting and you shouldn't trade it.

Mike

We're here to help -- just ask

For the best trading education, watch our webinars
Searching for trading reviews? Review this list

Follow us on Twitter, YouTube, and Facebook

Support our community as an Elite Member:
https://futures.io/elite/
Follow me on Twitter Visit my futures io Trade Journal Started this thread
The following 4 users say Thank You to Big Mike for this post:
 
(login for full post details)
  #146 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


FABRICATORX View Post
Here's something I found in my own results - I have a system that trades the US markets well, all except one.

It performs well in ES, YM, ZB, ZN. I apply any iteration of it to NQ, and it is erratic and flat. It doesn't lose, but, it doesn't win either lol.

NQ is a very tough market to develop a strategy for. I thought it was just for me, but quite a few traders better than me have said the same thing...

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


Big Mike View Post
Sorry for stepping in with my opinion in Kevin's AMA, but if a strategy fails to perform similarly on a highly correlated instrument, then it's a sure sign of curve fitting and you shouldn't trade it.

Mike

well maybe true in many cases but I disagree on that if it is inteded as a matter of fact. ES and YM are highly correlated markets(just to make an example that fit) but that doesn't mean that a strategy that works well on ES works the same way on YM, yes it should, in many cases it does, but it's not an if-then equation tu run or not a strategy, in my opinion.

My opinion instead is that there are very few strategies that are worth trading their own and I still didn't find any. But there may be a lot of average strategies that put into a portfolio could give you a quite stable performance. So the goal should be building a portfolio and make it grow, not working to find the best and robust strategy that will make you money forever(I know we all agree on it, but worth repeating)

The following user says Thank You to montanajtt for this post:
 
(login for full post details)
  #148 (permalink)
Barcelona Spain
 
 
Posts: 13 since Aug 2015
Thanks: 15 given, 7 received


Big Mike View Post
if a strategy fails to perform similarly on a highly correlated instrument, then it's a sure sign of curve fitting and you shouldn't trade it.

Mike

If you make the excercice to curve fitting a graph wouldn't you indirectly curve fit its highly correlated as well?


kevinkdog View Post
If you don't trust them, don't trade them.

Bought it!


kevinkdog View Post
You have the opinion that a strategy must work in multiple markets to be considered "robust." Maybe you should ask yourself why that has to be true. Why does a strategy that works on the ES also have to work on the Euro currency? Or, does an ES strategy have to work on the TF or NQ - and if so, how good does it have to be?

Examine your mindset about this requirement you have - that a strategy should work on multiple markets to be robust.

I didn't expect high performance on all markets for a single strategy. But I'm shocked at seeing a very good result on a single one and miserable results on another ones. I would have liked to see good results on one and at worst flat results on the others. Why do I have this paradigm? Well probably I've read too many times about this concept of robustness. Anyway if it weren't true which would be the sense of using CCI out of Commodities, or MAs everywhere, etc?

I hope my comments don't exceed your patience. But if I may, let me put my question in other way: For a mechanical trader all the rules to define a strategy are absolutely accurate, no exceptions. Once the strategy is 'manufactured' there's a mechanical process to test it and this last process should have its accurate rules. Here's the question. On these rules do you consider the results in just one market or do you expect some minimum for other markets as well?

Well, again thanks!

 
(login for full post details)
  #149 (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: 3,984 since Dec 2013
Thanks: 3,288 given, 7,799 received


FABRICATORX View Post
Here's something I found in my own results - I have a system that trades the US markets well, all except one.

It performs well in ES, YM, ZB, ZN. I apply any iteration of it to NQ, and it is erratic and flat. It doesn't lose, but, it doesn't win either lol.

If you rank those products in volatility order isn't NQ significantly more volatile than the others?

The following user says Thank You to SMCJB for this post:
 
(login for full post details)
  #150 (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

You know what, I have no idea lol. Is it?

Jimmy

-Jimmy
 
(login for full post details)
  #151 (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: 3,984 since Dec 2013
Thanks: 3,288 given, 7,799 received


SMCJB View Post
If you rank those products in volatility order isn't NQ significantly more volatile than the others?


FABRICATORX View Post
You know what, I have no idea lol. Is it?

VIX index values for each index... so yes NQ is the most volatile of the products you listed

VXN (~NQ) 18.07
VIX (~ES) 16.05
VXD (~YM) 14.7
TYVIX (~ZN) 4.96

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


SMCJB View Post
If you rank those products in volatility order isn't NQ significantly more volatile than the others?

The odd thing is usually MORE volatility in a market makes it EASIER to create a strategy...

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


Enric66 View Post
But if I may, let me put my question in other way: For a mechanical trader all the rules to define a strategy are absolutely accurate, no exceptions. Once the strategy is 'manufactured' there's a mechanical process to test it and this last process should have its accurate rules. Here's the question. On these rules do you consider the results in just one market or do you expect some minimum for other markets as well?

Well, again thanks!

I look at results for that market.

If results in other markets (if I even look) are good, that makes me feel a bit better.

If results in other markets (if I even look) are poor, that probably won't make me throw the system away.

I realize the pitfalls in this approach, but I have never been able to correlate future performance to this kind of metric.

Follow me on Twitter
The following 2 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #154 (permalink)
Izmir Turkey
 
 
Posts: 14 since Jul 2015
Thanks: 3 given, 26 received

Hello Kevin.

From the strategies that you created by your Strategy Factory rules, how many did you have to quit trading because they reached your max drawdown limit? Can you at least give a rough percentage? Thanks.

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


ilkan10 View Post
Hello Kevin.

From the strategies that you created by your Strategy Factory rules, how many did you have to quit trading because they reached your max drawdown limit? Can you at least give a rough percentage? Thanks.

Sorry, did not see this until just now. Somehow I don;t get e-mail notifications anymore...


Anyhow, I don't keep stats on this - I probably should. If I had to guess, I bet about 10% of strategies I stop trading because of poor performance.

Follow me on Twitter
The following user says Thank You to kevinkdog for this post:
 
(login for full post details)
  #156 (permalink)
Site Administrator
Swing Trader
Data Scientist & DevOps
Manta, Ecuador
 
Experience: Advanced
Platform: My own custom solution
Trading: Emini Futures
 
Big Mike's Avatar
 
Posts: 49,790 since Jun 2009
Thanks: 32,314 given, 97,615 received


kevinkdog View Post
Sorry, did not see this until just now. Somehow I don;t get e-mail notifications anymore...


Anyhow, I don't keep stats on this - I probably should. If I had to guess, I bet about 10% of strategies I stop trading because of poor performance.

If you aren't getting emails, you need to check your spam and mark us as not spam

Sent from my phone

We're here to help -- just ask

For the best trading education, watch our webinars
Searching for trading reviews? Review this list

Follow us on Twitter, YouTube, and Facebook

Support our community as an Elite Member:
https://futures.io/elite/
Follow me on Twitter Visit my futures io Trade Journal Started this thread
 
(login for full post details)
  #157 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


Big Mike View Post
If you aren't getting emails, you need to check your spam and mark us as not spam

Sent from my phone

Its weird, because it is not showing up as spam either. I did get a "here are your preferences" e-mail last week, though. I'll have to play around with it. Used to work fine...

Follow me on Twitter
 
(login for full post details)
  #158 (permalink)
Site Administrator
Swing Trader
Data Scientist & DevOps
Manta, Ecuador
 
Experience: Advanced
Platform: My own custom solution
Trading: Emini Futures
 
Big Mike's Avatar
 
Posts: 49,790 since Jun 2009
Thanks: 32,314 given, 97,615 received


kevinkdog View Post
Its weird, because it is not showing up as spam either. I did get a "here are your preferences" e-mail last week, though. I'll have to play around with it. Used to work fine...

In the last 7 days, you've been sent 48 emails and all were delivered successfully. The problem is on your side...



Here are the times for the most recent emails to you help you troubleshoot:



Mike

We're here to help -- just ask

For the best trading education, watch our webinars
Searching for trading reviews? Review this list

Follow us on Twitter, YouTube, and Facebook

Support our community as an Elite Member:
https://futures.io/elite/
Follow me on Twitter Visit my futures io Trade Journal Started this thread
 
(login for full post details)
  #159 (permalink)
Site Administrator
Swing Trader
Data Scientist & DevOps
Manta, Ecuador
 
Experience: Advanced
Platform: My own custom solution
Trading: Emini Futures
 
Big Mike's Avatar
 
Posts: 49,790 since Jun 2009
Thanks: 32,314 given, 97,615 received

It should also be noted that on Oct 16 8:48am you Unsubscribed from some things (can't tell what), but I notice your thread subscription settings are now set for no email by default.

You should check your profile settings and subscription settings if you did this by mistake.

Mike

We're here to help -- just ask

For the best trading education, watch our webinars
Searching for trading reviews? Review this list

Follow us on Twitter, YouTube, and Facebook

Support our community as an Elite Member:
https://futures.io/elite/
Follow me on Twitter Visit my futures io Trade Journal Started this thread
 
(login for full post details)
  #160 (permalink)
Site Administrator
Swing Trader
Data Scientist & DevOps
Manta, Ecuador
 
Experience: Advanced
Platform: My own custom solution
Trading: Emini Futures
 
Big Mike's Avatar
 
Posts: 49,790 since Jun 2009
Thanks: 32,314 given, 97,615 received

Your email server is responding with 452's, which is an out of resources/out of memory error.

I also see GL appended, which could be greylisting. That's fine, I use greylisting on my server as well to reduce spam -- but your greylist isn't setup correctly if we aren't automatically whitelisted after a while of sending emails. Otherwise, all emails would be delayed continuously.



Your server is also an open relay for spam it would seem according to a quick test.

https://mxtoolbox.com/SuperTool.aspx?action=smtp%3a66.96.140.65&run=toolpage

Mike

We're here to help -- just ask

For the best trading education, watch our webinars
Searching for trading reviews? Review this list

Follow us on Twitter, YouTube, and Facebook

Support our community as an Elite Member:
https://futures.io/elite/
Follow me on Twitter Visit my futures io Trade Journal Started this thread
The following user says Thank You to Big Mike for this post:
 
(login for full post details)
  #161 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received

Thanks for checking. I have idea what is going on, but I'll talk to the domain people.

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

Hopefully I fixed the problem, thanks for the help @Big Mike!

Follow me on Twitter
The following user says Thank You to kevinkdog for this post:
 
(login for full post details)
  #163 (permalink)
Barcelona Spain
 
 
Posts: 13 since Aug 2015
Thanks: 15 given, 7 received


kevinkdog View Post
I look at results for that market.

If results in other markets (if I even look) are good, that makes me feel a bit better.

If results in other markets (if I even look) are poor, that probably won't make me throw the system away.

I realize the pitfalls in this approach, but I have never been able to correlate future performance to this kind of metric.

Hi! Thank you very much for your kind and precise response. Very helpful indeed.

The following user says Thank You to Enric66 for this post:
 
(login for full post details)
  #164 (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: 3,984 since Dec 2013
Thanks: 3,288 given, 7,799 received

Some advice please Kevin.

Let's say I back tested and tuned a model on 10 years of data 2004-2013. Not that it matters but lets say my instrument isn't something simple like ES, but say an energy spread, that is generally mean reverting.

I then forwarded tested my data on 2014 and it performed well so I went live with my model in 2015 and it has performed well also.

As I go into 2016 should I still be using the model tuned on the original 10 years of data 2004-2013 data? Should I update that to 11 years 2004-2014 or keep it 10 years but move it forward 2005-2014, then re-tune, and walk forward on 2015 data just to make sure its still good? Or should I even consider re-tuning on the 12 years 2004-2015 data or even the most recent 10 years 2006-2015?

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


SMCJB View Post
Some advice please Kevin.

Let's say I back tested and tuned a model on 10 years of data 2004-2013. Not that it matters but lets say my instrument isn't something simple like ES, but say an energy spread, that is generally mean reverting.

I then forwarded tested my data on 2014 and it performed well so I went live with my model in 2015 and it has performed well also.

As I go into 2016 should I still be using the model tuned on the original 10 years of data 2004-2013 data? Should I update that to 11 years 2004-2014 or keep it 10 years but move it forward 2005-2014, then re-tune, and walk forward on 2015 data just to make sure its still good? Or should I even consider re-tuning on the 12 years 2004-2015 data or even the most recent 10 years 2006-2015?

That is a good question. I'm not sure there is a correct answer, but there are some alternatives...

1. What you describe is what many people call a standard "out of sample" test. The typical way these are run do not have any mechanism for re-optimizing. So, whatever model you initially chose, which also worked on out of sample data, would be used indefinitely, and you'd never re-optimize. You could trade this model for 10-20 years and the model would never change. It may or may not hold up.

2. But, you could have done this as a walkforward test with a moving window. Then every year, you'd re-tune your model with the most recent 10 years of data. So, your model could change every year. This is walkforward with unanchored testing (the in sample optimization window moves).

3. Finally, you could re-optimize your model every year, but use all the data available. So, the first optimization is 10 years of data. Next one will use 11 years or data, and so on. The model still gets re-optimized every year. This is a walkforward optimization that is anchored (start point never moves).


Which is best? I guess it depends who you ask. I personally use option 2. I don't like #1 because it never changes, and I don't like #3 because old data keeps impacting the optimization well into the future.


The one thing about your case is that it is not really walkforward optimization yet, since you only had one out of sample period. That one period of out of sample might not be significant - that's why true walkforward testing has 10-20+ out of sample periods.


Question for you: how much does the model change between these 3 alternatives:

1. keep original model
2. re-optimize model with 10 years of data
3. re-optimize model with 11 years of data

Is there a huge difference in the models?

Follow me on Twitter
The following 6 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #166 (permalink)
OC, California, USA
 
Experience: Advanced
Platform: IB/TWS, NinjaTrader, ToS
Broker: IB, ToS, Kinetick
Trading: stocks, options, futures, VIX
 
shodson's Avatar
 
Posts: 1,958 since Jun 2009
Thanks: 528 given, 3,648 received

4. stop re-optimizing, avoid systems that require optimization to be successful (I guess that's the same as #1)

Follow me on Twitter Visit my futures io Trade Journal
The following 2 users say Thank You to shodson for this post:
 
(login for full post details)
  #167 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


shodson View Post
4. stop re-optimizing, avoid systems that require optimization to be successful (I guess that's the same as #1)

Very good point!

I know some very good traders who do either or both of these things: create models with nothing to optimize, and/or create models that they never reoptimize.

I personally like walkforward, but I know people can and do have success without walkforward.

The key is to have a process/method that proves itself with real money.

Follow me on Twitter
The following 2 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #168 (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: 3,984 since Dec 2013
Thanks: 3,288 given, 7,799 received

Thanks Kevin.

It's interesting what you said in 2) as that relates to the next part of my question.

When I originally started on this model, I arbitrarily picked the last 11 years (04-14), 10 years to look at (04-13), and 1 year (14) as an out of sample test. Once I completed the first model (which is the model I'm actually still trading today) I started delving deeper into the data. I looked at using the last 9, 8, 7, 6 & 5 years rather than 10. The results showed that the model with the best fit used the last 7 years (07-13) rather than 10 years (04-14) of data. I could tell from looking at the models that the higher energy prices of the more recent years (2008, 10-13) where heavily influencing the models. Since the 7 year models results weren't significantly better than the 10 year, I decided to just stick with the original 10 year.

I actually then built a new model, that included a 'year variable'. This model was significantly better than any of the other models. The problem is the addition of the year variable gave values for 2015 significantly higher than anything previously seen, and of course 2016 would probably be even higher. Despite this model having better results I did not use it, and kept with the original 10 year model.

As we all know, energy prices have plummeted in the last year. The model I am using (built based upon 10 years (04-14)) has performed admirably. The model based upon 7 years of data would have been profitable, but not nearly as good. The model that included the 'year variable' would have got destroyed.

I'm comfortable with my decision to use the 10 year vs the 7 year, but by choosing the 10 year over the 'year variable' I feel like I allowed my personal bias to overrule what should be a more systematic and statistical approach. The fact that my personal bias was correct, obviously makes me feel good, but I'm still concerned I've contaminated the process.

So getting back to your point 2
you could have done this as a walkforward test with a moving window. Then every year, you'd re-tune your model with the most recent 10 years of data. So, your model could change every year. This is walkforward with unanchored testing (the in sample optimization window moves).
This is actually what I was planning to do. The problem is, I already know what happened in 2015. If I roll my window forward to 04-14 with an out of sample 2015, I know what the results will be. I know that any model more heavily based upon the recent high energy prices will perform far worse than a model with a longer tenor of data. I strongly suspect that a new model with a "polynomial year variable" (something like -(year-2011.5)^2) would probably perform quite well, but I know that because I know energy prices have had a concave trajectory over the last 15 years. I feel like whatever I do, my personal bias's/knowledge are corrupting the process.

I know there's no actual question in there, but I was curious if you have any additional thoughts on the matter?

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

You personal biases may be impacting things, but that is not necessarily a bad thing. Your biases might actually be helping you to make a better decision.

Based on what you've done already, it is hard to recommend a way forward. Like you say, you already know the results, so trying to formalize this into a process probably doesn't make sense.

If I think of a way around this, I'll post it.

Follow me on Twitter
The following 2 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #170 (permalink)
SE Asia / Canada
 
Experience: Intermediate
Platform: FXCM's Trading Station
Broker: Darwinex, FXCM, Tradingview
Trading: Forex and CFD's
 
Posts: 114 since Jun 2010
Thanks: 26 given, 109 received

Hi Kevin,

Any more youtube videos planned in the close future? those are really good

cheers,

Follow me on Twitter Visit my futures io Trade Journal
The following user says Thank You to DobermanTrading for this post:
 
(login for full post details)
  #171 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


totantaz View Post
Hi Kevin,

Any more youtube videos planned in the close future? those are really good

cheers,

Glad you like them! No more videos planned, busy instead doing my own trading, doing some interesting research and working with clients....

Follow me on Twitter
The following user says Thank You to kevinkdog for this post:
 
(login for full post details)
  #172 (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: 3,984 since Dec 2013
Thanks: 3,288 given, 7,799 received


kevinkdog View Post
You personal biases may be impacting things, but that is not necessarily a bad thing. Your biases might actually be helping you to make a better decision.

Based on what you've done already, it is hard to recommend a way forward. Like you say, you already know the results, so trying to formalize this into a process probably doesn't make sense.

If I think of a way around this, I'll post it.

Thanks Kevin.

So given that, another option is to recalibrate on the last 10 years of data, or the entire 12 years of data, without any out of sample data?

Final question would you ever trade 2 very similar but slightly different models to get some diversification, or just stick with the one you think is best? Was thinking that since the original model (04-13) has done so well that I might allocate half the position to that, and half the position to the new most recent 10 years (06-15). The parameters will be similar but slightly different.

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


SMCJB View Post
Thanks Kevin.

So given that, another option is to recalibrate on the last 10 years of data, or the entire 12 years of data, without any out of sample data?

Final question would you ever trade 2 very similar but slightly different models to get some diversification, or just stick with the one you think is best? Was thinking that since the original model (04-13) has done so well that I might allocate half the position to that, and half the position to the new most recent 10 years (06-15). The parameters will be similar but slightly different.

That is another option...

I would certainly think about trading 2 similar models, instead of trying to pick the "best" one and trading it double size.

You'll get a more average return (you won't get the best return, but you won't get the worst either), but the biggest thing is you save emotional capital by not stressing over "did I pick the best one?" That alone might be well worth the price for "blending" the two together.

Follow me on Twitter
The following 2 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #174 (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: 3,984 since Dec 2013
Thanks: 3,288 given, 7,799 received

Thanks @kevinkdog,
As always your insight is very interesting and valuable.
Really appreciate the responses.

The following user says Thank You to SMCJB for this post:
 
(login for full post details)
  #175 (permalink)
Cancun, Mexico
 
Experience: Advanced
Trading: Stock Index Futures / CFDs
 
Anagami's Avatar
 
Posts: 865 since Dec 2010
Thanks: 603 given, 1,951 received

@kevinkdog

Hi Kevin,

I am in the process of reading your book, you did a fantastic job.

Question: given your extensive testing experience, what is the shortest timeframe that you found any profitable system on? For example, did you ever find anything on 5 min? 3 min? 15 min? Or are slippage / cost too prohibitive on that scale?

Thank you!

"The mind is its own place, and in itself can make a heaven of hell, a hell of heaven." - Milton
The following 2 users say Thank You to Anagami for this post:
 
(login for full post details)
  #176 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


Anagami View Post
@kevinkdog

Hi Kevin,

I am in the process of reading your book, you did a fantastic job.

Question: given your extensive testing experience, what is the shortest timeframe that you found any profitable system on? For example, did you ever find anything on 5 min? 3 min? 15 min? Or are slippage / cost too prohibitive on that scale?

Thank you!

Thanks for the nice comment on my book (I love to see reviews like that on Amazon! hint hint)

I have strategies on the lowest timeframe I have tested: 1 minute.

That being said, most of my strategies tend to use daily bars.

Good Luck!

Follow me on Twitter
The following 4 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #177 (permalink)
Calgary
 
Experience: None
Platform: TradeStation, MT4
Trading: ES, Stocks
 
Posts: 73 since Aug 2015
Thanks: 4 given, 10 received

Kevin,

I have the following two lines of code that runs on the 15M chart.

 
Code
if MarketPosition (0) =-1 then BUYTOCOVER ("close sell") NEXT BAR OPEN at NEXT BAR LIMIT ;
BUY ("enter buy") MinList (NumContracts, max_contract) CONTRACT NEXT BAR OPEN at NEXT BAR+BuyLimit_Offset LIMIT ;


How can I rewrite these codes so that I can attach the strategy to the 1M chart while referencing the 15M chart's NEXT BAR OPEN at NEXT BAR LIMIT?

I would like to avoid the error of " Open Next Bar type strategies calculation is not permitted on multiple data streams."

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


fiverr View Post
Kevin,

I have the following two lines of code that runs on the 15M chart.

 
Code
if MarketPosition (0) =-1 then BUYTOCOVER ("close sell") NEXT BAR OPEN at NEXT BAR LIMIT ;
BUY ("enter buy") MinList (NumContracts, max_contract) CONTRACT NEXT BAR OPEN at NEXT BAR+BuyLimit_Offset LIMIT ;


How can I rewrite these codes so that I can attach the strategy to the 1M chart while referencing the 15M chart's NEXT BAR OPEN at NEXT BAR LIMIT?

I would like to avoid the error of " Open Next Bar type strategies calculation is not permitted on multiple data streams."


So, it seems like using multiple datastreams is out of the question.

I would try to fake it then, by capturing the open price of each 15 minute bar in a variable.

Pseudo code would look like this:

if time minute ends in 59,14,29, or 44 then // for example: 12:59, 2:14, etc.
time15 = open next bar;


Buytocover next bar at time15 limit;



This is a tricky problem. I am no expert coder either - I focus more on creating simple strategies.

If my idea does not work, I'd post the question in the Tradestation question section here, or even the Tradestation.com user form.

Good Luck!

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

Kevin,

Thanks for the coding tip. BTW, this is what I am trying to accomplish. Please let me know if I am trying to reinvent the wheel.

See below backtesting results in MC.




As you can see, the original code is referencing 30M, and I am using 1M bar magnifier to obtain the backtesting results. When I look at my backtesting results (list of trades), the resolution step is 30 minutes. So I don't know whether the trade entered at 9:01AM or 9:28AM.

When I use 1M code to reference 30M logics, I obtain a 1-minute resolution. See below.



As you can see above, I know exactly that the trade entered at 9:03M and exited at 9:13AM. This way I can compare the real trades with the backtesting results to measure slippage, signal accuracy, and reliability.

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


fiverr View Post
Kevin,

Thanks for the coding tip. BTW, this is what I am trying to accomplish. Please let me know if I am trying to reinvent the wheel.

See below backtesting results in MC.




As you can see, the original code is referencing 30M, and I am using 1M bar magnifier to obtain the backtesting results. When I look at my backtesting results (list of trades), the resolution step is 30 minutes. So I don't know whether the trade entered at 9:01AM or 9:28AM.

When I use 1M code to reference 30M logics, I obtain a 1-minute resolution. See below.



As you can see above, I know exactly that the trade entered at 9:03M and exited at 9:13AM. This way I can compare the real trades with the backtesting results to measure slippage, signal accuracy, and reliability.

Your approach sounds reasonable to me. If it ends up not working correctly, please post an update and hopefully it can get figured out.



Kevin

Follow me on Twitter
 
(login for full post details)
  #181 (permalink)
Gits (Hooglede) Belgium
 
Experience: Master
Platform: NinjaTrader, Proprietary,
Broker: Ninjabrokerage/IQfeed + Synthetic datafeed
Trading: 6A, 6B, 6C, 6E, 6J, 6S, ES, NQ, YM, AEX, CL, NG, ZB, ZN, ZC, ZS, GC
 
rleplae's Avatar
 
Posts: 2,991 since Sep 2013
Thanks: 2,437 given, 5,801 received

Hi Kevin

I have a question :

What is in your opinion the best order platform, with that i mean, i have a stand-alone bot, it takes in data-feed, does all the calculations and generates and manages the trades.

I build this stand-alone, to have structured code, compared to many different indicators (this has a significant development price). But i control it from end-2-end, which is an advantage.

Today i inject orders into NinjaTrader, but the ATI api is kind of limited in my opinion, if you touch the orders in chart trader, through the API you are blind. I can work around going to the sdf database, but that is not officially supported. The hole setup is also not 'rock solid' as NinjaTrader has it's own character and crashes from time to time especially if the markets are busy and you 'poke' to frequent through the ATI. The nice thing is that i can connect to a big series of brokers without extra effort.

Now my question, is there a better solution for broker abstraction, that allows better control over the order life cycle ?

Thanks,
Ron

Follow me on Twitter Visit my futures io Trade Journal
The following 2 users say Thank You to rleplae for this post:
 
(login for full post details)
  #182 (permalink)
 
 
Posts: 2,979 since Jul 2012
Thanks: 1,576 given, 5,906 received


rleplae View Post
Hi Kevin

I have a question :

What is in your opinion the best order platform, with that i mean, i have a stand-alone bot, it takes in data-feed, does all the calculations and generates and manages the trades.

I build this stand-alone, to have structured code, compared to many different indicators (this has a significant development price). But i control it from end-2-end, which is an advantage.

Today i inject orders into NinjaTrader, but the ATI api is kind of limited in my opinion, if you touch the orders in chart trader, through the API you are blind. I can work around going to the sdf database, but that is not officially supported. The hole setup is also not 'rock solid' as NinjaTrader has it's own character and crashes from time to time especially if the markets are busy and you 'poke' to frequent through the ATI. The nice thing is that i can connect to a big series of brokers without extra effort.

Now my question, is there a better solution for broker abstraction, that allows better control over the order life cycle ?

Thanks,
Ron

Hi Ron -

The level of depth you seek is out of my league - way beyond my knowledge base. I have been running Tradestation automated for years, and never really searched for an alternative (I have not seen a pressing need to). I have a pretty solid backup plan in place if Tradestation brokerage and/or platform suddenly goes away, but it is nowhere near what you have done.

Sorry, I wish I had a better answer for you.

Kevin

Follow me on Twitter
 
(login for full post details)
  #183 (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: 3,984 since Dec 2013
Thanks: 3,288 given, 7,799 received

@rleplae Have you looked at Trading Technologies XTAPI? I have no personal experience but I gather it's top notch. Not as cheap as NT or Tradestation though.

The following user says Thank You to SMCJB for this post:
 
(login for full post details)
  #184 (permalink)
Gits (Hooglede) Belgium
 
Experience: Master
Platform: NinjaTrader, Proprietary,
Broker: Ninjabrokerage/IQfeed + Synthetic datafeed
Trading: 6A, 6B, 6C, 6E, 6J, 6S, ES, NQ, YM, AEX, CL, NG, ZB, ZN, ZC, ZS, GC
 
rleplae's Avatar
 
Posts: 2,991 since Sep 2013
Thanks: 2,437 given, 5,801 received


SMCJB View Post
@rleplae Have you looked at Trading Technologies XTAPI? I have no personal experience but I gather it's top notch. Not as cheap as NT or Tradestation though.

vaguely, any clue on the pricing ?

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

Kevin,

What is your take on Walk Forward Optimization? Are you for rolling forward testing or anchored WFO?

BTW, I have come across several PhDs who believes that WFO is curve fitting at its best.

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


fiverr View Post
Kevin,

What is your take on Walk Forward Optimization? Are you for rolling forward testing or anchored WFO?

BTW, I have come across several PhDs who believes that WFO is curve fitting at its best.

I use walkforward optimization on almost all my strategies. I usually use rolling forward walkforward. For certain fitness functions, anchored WF is more appropriate.

Are the PhDs traders?

Walkforward can be curve fit, if you do it incorrectly.

Follow me on Twitter
The following 4 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #187 (permalink)
Calgary
 
Experience: None
Platform: TradeStation, MT4
Trading: ES, Stocks
 
Posts: 73 since Aug 2015
Thanks: 4 given, 10 received

Kevin,

I understand that you use Stratopt for WFO and WFP. Have you used Diamond Backtesting with Walk Forward Manager (BTWFMgr) by profsoftware? It will be interesting if you can create another video comparing Stratopt and BTWFMgr.

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


kevinkdog View Post
For certain fitness functions, anchored WF is more appropriate. Walkforward can be curve fit, if you do it incorrectly.

Kevin,

Thanks for your prompt reply. Can you elaborate more on anchored WF and also how Walkforward can be curve fitted?

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


fiverr View Post
Kevin,

I understand that you use Stratopt for WFO and WFP. Have you used Diamond Backtesting with Walk Forward Manager (BTWFMgr) by profsoftware? It will be interesting if you can create another video comparing Stratopt and BTWFMgr.

Never used Diamond. No plans to use it at this point.

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


fiverr View Post
Kevin,

Thanks for your prompt reply. Can you elaborate more on anchored WF and also how Walkforward can be curve fitted?

Anchored vs. Unanchored

Unanchored wf might not be correct, if you use a fitness function like drawdown - depending how your walkforward software calculates it. It is hard to explain, since it depends on the particular software. Example why this MIGHT matter:

Date1: Jan 1, 2000 Net Profit = XXXNP, Max drawdown= XXXDD
Date2: Jan 1, 2010 Net Profit = YYYNP, Max drawdown= YYYDD

Net Profit, from Date1 to Date2 = YYYNP - XXXNP
Max Drawdown though is not YYYDD-XXXDD


Curve Fitting Walkforward

2 examples:

A. You run walkforward, get results and then think "I can improve that with a filter" and you do this say 4 or 5 times. Everything improves and you know you've made out of sample walkforward results better. Problem is your walkforward is not really out of sample anymore - it is some conglomeration of out of sample and curve fitted results.

B. You pick 10 combinations of IN/OUT to do your walkforward. You pick the best one to use going forward.

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


fiverr View Post
Kevin,

What is your take on Walk Forward Optimization? Are you for rolling forward testing or anchored WFO?

BTW, I have come across several PhDs who believes that WFO is curve fitting at its best.

@fiverr -

Can you expand upon the several PhDs (trading experience, background) who say WFO is curve fitting? I'm curious how they are doing their development that leads them to this conclusion.

Thanks!

Follow me on Twitter
The following user says Thank You to kevinkdog for this post:
 
(login for full post details)
  #192 (permalink)
Calgary
 
Experience: None
Platform: TradeStation, MT4
Trading: ES, Stocks
 
Posts: 73 since Aug 2015
Thanks: 4 given, 10 received

The comment came from the program director of Algorithmic Trader Association. He believes that WFO is the pinnacle of curve fitting.

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


fiverr View Post
The comment came from the program director of Algorithmic Trader Association. He believes that WFO is the pinnacle of curve fitting.

Thanks. My experience is totally in conflict with that (unless the WFO is incorrectly done), but that is what makes a market - different people with different ideas.

Follow me on Twitter
The following 3 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #194 (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: 3,984 since Dec 2013
Thanks: 3,288 given, 7,799 received


fiverr View Post
The comment came from the program director of Algorithmic Trader Association. He believes that WFO is the pinnacle of curve fitting.

Was that Alex, Doron or somebody else? Just curious.

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


fiverr View Post
The comment came from the program director of Algorithmic Trader Association. He believes that WFO is the pinnacle of curve fitting.

I think Kevin Davey has proven that it works just fine as long as you know what you are doing.

The following user says Thank You to Mabi for this post:
 
(login for full post details)
  #196 (permalink)
Site Moderator
 
 
sam028's Avatar
 
Posts: 3,665 since Jun 2009
Thanks: 3,787 given, 4,494 received

Well, if WFO is not an option I wonder what's working... Rolling dices maybe?
I'll be curious to see what was really wrote/said about this, there might be some kind of misunderstanding somewhere.

Success requires no deodorant! (Sun Tzu)
Follow me on Twitter
The following 2 users say Thank You to sam028 for this post:
 
(login for full post details)
  #197 (permalink)
Calgary
 
Experience: None
Platform: TradeStation, MT4
Trading: ES, Stocks
 
Posts: 73 since Aug 2015
Thanks: 4 given, 10 received

Has any taken Andrea Unger's trading course? He also does not believe in WFO.

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


fiverr View Post
Has any taken Andrea Unger's trading course? He also does not believe in WFO.

First, I am sure that Andrea's course is really good. I taught a live 4 day class with him in New York last April 2016, and I picked up quite a few good ideas/concepts from him. He is a very good trader. The industry needs more trader/educators like him.

As far as "believe in WFO" I know he does not use it, so I decided to ask him. He does not have an account here, so he allowed me reply for him:

"Hi Kevin,
I've been asked recently twice about WFO and in both cases I stated that I don't use it, I don't recall any occasion where I said I don't "believe" in it. In fact I will include a chapter of WFO in my Strategy Evaluation Course about it. You can answer on my behalf .

Ciao
Andrea"



So my take on this is you can be successful without walkforward (Andrea is). You can be successful with walkforward (I am). More than one way to skin a cat...

Follow me on Twitter
The following 7 users say Thank You to kevinkdog for this post:
 
(login for full post details)
  #199 (permalink)
sweden
 
Experience: Advanced
Platform: NinjaTrader,MetaTrader
Trading: futures, FX
 
Mabi's Avatar
 
Posts: 141 since Oct 2010
Thanks: 121 given, 135 received

In regards to WFO I find that Ninjatrader not necessarily have given the best result in order to have a viable trading result going forward and that the settings it has found could be equally or similar using other settings. The best thing is of course if you do not have to change your settings for the next period. Scalping strategies can be very sensitive to larger differences in stop an targets from period to period which will make your future results a looser if you actually used the setting NT comes up with especially if they differ to much from previous period. It would be better if you were given a matrix of each period of workable settings in order to have a better change of picking an median setting that might be closer to your overall backtest results. So that said I do not use the WFO results as is without further testing.

 
(login for full post details)
  #200 (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: 3,984 since Dec 2013
Thanks: 3,288 given, 7,799 received


fiverr View Post
The comment came from the program director of Algorithmic Trader Association. He believes that WFO is the pinnacle of curve fitting.


SMCJB View Post
Was that Alex, Doron or somebody else? Just curious.


kevinkdog View Post
He does not have an account here, so he allowed me reply for him:

"Hi Kevin,
I've been asked recently twice about WFO and in both cases I stated that I don't use it, I don't recall any occasion where I said I don't "believe" in it. In fact I will include a chapter of WFO in my Strategy Evaluation Course about it. You can answer on my behalf ."

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

The following user says Thank You to SMCJB for this post:

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