NexusFi: Find Your Edge


Home Menu

 





Why Use Strategy Optimization


Discussion in NinjaTrader

Updated
      Top Posters
    1. looks_one goodoboy with 5 posts (3 thanks)
    2. looks_two ratfink with 2 posts (3 thanks)
    3. looks_3 Quick Summary with 1 posts (0 thanks)
    4. looks_4 Seahn with 1 posts (0 thanks)
    1. trending_up 1,446 views
    2. thumb_up 9 thanks given
    3. group 4 followers
    1. forum 9 posts
    2. attach_file 0 attachments




 
Search this Thread

Why Use Strategy Optimization

  #1 (permalink)
goodoboy
Houston
 
Posts: 380 since Dec 2016
Thanks Given: 344
Thanks Received: 246

Hello,



I been developing and back testing a few trading strategies in NT7. I am still a bit new.

I was watching the video on how to create strategy. The strategy shows the back test made good money.

But at times 1:40 and 19:40 in the video he says "DO not use this strategy cause I assure you it will not make money in forward testing"

He is doing optimization and strategy shows to make money.

I don't understand why trader can't use this strategy if optimize settings shows the strategy made money.

What is the purpose of Optimization if can't use the settings to make money?

Thanks,

Reply With Quote
Thanked by:

Can you help answer these questions
from other members on NexusFi?
NexusFi Journal Challenge - April 2024
Feedback and Announcements
Better Renko Gaps
The Elite Circle
Futures True Range Report
The Elite Circle
ZombieSqueeze
Platforms and Indicators
New Micros: Ultra 10-Year & Ultra T-Bond -- Live Now
Treasury Notes and Bonds
 
Best Threads (Most Thanked)
in the last 7 days on NexusFi
Get funded firms 2023/2024 - Any recommendations or word …
61 thanks
Funded Trader platforms
39 thanks
Battlestations: Show us your trading desks!
24 thanks
NexusFi site changelog and issues/problem reporting
24 thanks
The Program
17 thanks
  #3 (permalink)
 
ratfink's Avatar
 ratfink 
Birmingham UK
Market Wizard
 
Experience: Intermediate
Platform: NinjaTrader
Broker: TST/Rithmic
Trading: YM/Gold
Posts: 3,633 since Dec 2012
Thanks Given: 17,423
Thanks Received: 8,425



goodoboy View Post

What is the purpose of Optimization if can't use the settings to make money?

Thanks,

To keep programmers employed, burn CPU cycles, and find folks something else to do, this makes them feel better while they're losing money, until they figure out what might actually work.

Travel Well
Visit my NexusFi Trade Journal Reply With Quote
  #4 (permalink)
goodoboy
Houston
 
Posts: 380 since Dec 2016
Thanks Given: 344
Thanks Received: 246


ratfink View Post
To keep programmers employed, burn CPU cycles, and find folks something else to do, this makes them feel better while they're losing money, until they figure out what might actually work.

Thanks ratfink for response,

So optimization gives programmers jobs? can you please explain here?

Yes, I agree the optimization takes a long time to run.

Can you please explain what you mean by this "this makes them feel better while they're losing money, until they figure out what might actually work."?

Thanks

Reply With Quote
Thanked by:
  #5 (permalink)
 
ratfink's Avatar
 ratfink 
Birmingham UK
Market Wizard
 
Experience: Intermediate
Platform: NinjaTrader
Broker: TST/Rithmic
Trading: YM/Gold
Posts: 3,633 since Dec 2012
Thanks Given: 17,423
Thanks Received: 8,425


goodoboy View Post
Thanks ratfink for response,

So optimization gives programmers jobs? can you please explain here?

Yes, I agree the optimization takes a long time to run.

Can you please explain what you mean by this "this makes them feel better while they're losing money, until they figure out what might actually work."?

Thanks

Writing countless optimisation systems over the decades has kept many employed, obviously excuse the overall tongue-in-cheek nature of my comment. Ditto I think it makes people feel better because they think the optimisation system is doing something productive for them, when in most cases it is an illusion.

Many users of optimisation do so under the mistaken belief that the past can predict the future, so if we have enough data and optimise accordingly, then it will predict the future better. Under this argument more data and more optimisation is therefore always seen as a good thing, sadly it only worsens the problem of curve fitting, usually in the absence of a meaningful model, at some level.

However, a knowledge of where we are in relation to the past and similar conditions that have occurred in the past is obviously an asset. If this is used in conjunction with a useful model on whatever timeframe you work, then useful results can be achieved, but in general the facts speak for themselves - most users of optimisation do not get much in the way of positive benefits, systems fail when they meet the real world and live data.

If you are serious in this area I would recommend looking at the work of folks like Kevin Davey @kevinkdog who do seem to 'get it' and make it perform profitably.

Cheers

Travel Well
Visit my NexusFi Trade Journal Reply With Quote
Thanked by:
  #6 (permalink)
 
SMCJB's Avatar
 SMCJB 
Houston TX
Legendary Market Wizard
 
Experience: Advanced
Platform: TT and Stellar
Broker: Advantage Futures
Trading: Primarily Energy but also a little Equities, Fixed Income, Metals and Crypto.
Frequency: Many times daily
Duration: Never
Posts: 5,041 since Dec 2013
Thanks Given: 4,375
Thanks Received: 10,192


ratfink View Post
If you are serious in this area I would recommend looking at the work of folks like Kevin Davey @kevinkdog who do seem to 'get it' and make it perform profitably.

In this thread here
KJ Trading Systems Kevin Davey - Ask Me Anything (AMA)
And this book here
Building Winning Algorithmic Trading Systems: A Trader's Journey From Data Mining to Monte Carlo Simulation to Live Trading (Wiley Trading)
And in half a dozen webinars

Reply With Quote
Thanked by:
  #7 (permalink)
 
Seahn's Avatar
 Seahn 
New York, New Jersey/USA
 
Experience: Intermediate
Platform: NinjaTrader
Trading: Futures
Posts: 161 since Jan 2013
Thanks Given: 63
Thanks Received: 274

Optimizing a strategy does nothing more than curve fit the parameters to past data. It does virtually nothing to improve the strategy in the future. I learned this lesson many moons ago.

All optimization routines in software packages do is help sell the software,

Wow look at the advanced optimization capabilities of our software you will be able to fine tune your strategy for maximum profits at the click of a button.........

Reply With Quote
  #8 (permalink)
goodoboy
Houston
 
Posts: 380 since Dec 2016
Thanks Given: 344
Thanks Received: 246


ratfink View Post
Writing countless optimisation systems over the decades has kept many employed, obviously excuse the overall tongue-in-cheek nature of my comment. Ditto I think it makes people feel better because they think the optimisation system is doing something productive for them, when in most cases it is an illusion.

Many users of optimisation do so under the mistaken belief that the past can predict the future, so if we have enough data and optimise accordingly, then it will predict the future better. Under this argument more data and more optimisation is therefore always seen as a good thing, sadly it only worsens the problem of curve fitting, usually in the absence of a meaningful model, at some level.

However, a knowledge of where we are in relation to the past and similar conditions that have occurred in the past is obviously an asset. If this is used in conjunction with a useful model on whatever timeframe you work, then useful results can be achieved, but in general the facts speak for themselves - most users of optimisation do not get much in the way of positive benefits, systems fail when they meet the real world and live data.

If you are serious in this area I would recommend looking at the work of folks like Kevin Davey @kevinkdog who do seem to 'get it' and make it perform profitably.

Cheers

Thank you very much for the explanation. I am reading Kevin Book right now and yes, I ask him questions before. He is good guy.

Reply With Quote
Thanked by:
  #9 (permalink)
goodoboy
Houston
 
Posts: 380 since Dec 2016
Thanks Given: 344
Thanks Received: 246



Thank you SMCJB, I am reading the book now.

Thanks,

Reply With Quote
  #10 (permalink)
goodoboy
Houston
 
Posts: 380 since Dec 2016
Thanks Given: 344
Thanks Received: 246



Seahn View Post
Optimizing a strategy does nothing more than curve fit the parameters to past data.

Thank you Seahn for the explanation,

So when optimizing, the software takes the data from past and find some parameters that would have produce a profit for that data it optimized?

Thanks

Reply With Quote




Last Updated on May 8, 2017


© 2024 NexusFi™, s.a., All Rights Reserved.
Av Ricardo J. Alfaro, Century Tower, Panama City, Panama, Ph: +507 833-9432 (Panama and Intl), +1 888-312-3001 (USA and Canada)
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.
About Us - Contact Us - Site Rules, Acceptable Use, and Terms and Conditions - Privacy Policy - Downloads - Top
no new posts