Do you know the trap of overfitting: https://www.mql5.com/en/articles/652
MQL5 Cookbook: Reducing the Effect of Overfitting and Handling the Lack of Quotes
- 2013.09.24
- Anatoli Kazharski
- www.mql5.com
I believe a lot of traders have repeatedly puzzled over the optimal parameters for their trading systems. Indeed, a trading algorithm alone is not enough. One needs to see how it can further be used. Whatever trading strategy you use, whether it's simple or complex, with a single or multiple instruments, you cannot avoid the question of what...
Carl Schreiber:
Do you know the trap of overfitting: https://www.mql5.com/en/articles/652
Do you know the trap of overfitting: https://www.mql5.com/en/articles/652
I've downloaded the TickStory-Lite v1.5.3. My MT4 has the verison of 4.00 Build 1090 (19 May 2017). I am not sure if this is a problem of compatibility?
Carl Schreiber:
Do you know the trap of overfitting: https://www.mql5.com/en/articles/652
Do you know the trap of overfitting: https://www.mql5.com/en/articles/652
I don't think my problem is of "over fitting". If it is a "over fitting", where does this over fitting come from? From the optimazation using the historical data from my MT4 broker? Or from TickStory?
"Over fitting" means different. If my backtesting result quite differes by different time period, this maybe the over-fitting. But I do the optimazation on the same time period with two different historical data sources and got quite different results, is this "over-fitting"? NO!I do not use the tick datas. I've downloadsed the minute datas from tickstory.com and use the "PeriodConverter" to convert them to 5min, 15min etc.
Your wasting your time.
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
Since many of the MT4 brokers provide very short historical data, so I download the historical datas from tickstory.com. After I do the optimazation backtesting and have chosen the optimal parameter set, I use this to run a back testing by using the "Every tick..." from the broker. But the result is very terrible.
I wonder if the other also have such a problem?
I am not sure this has something to do with the TickStory-Lite versin and the MT4 version?