You may want to try optimizing on the last year and backtest out of
sample on previous years. herman intermilan04 wrote: __._,_.___Hi Sebastian, "you can't really know that your system has "broken down" until you get the final results on January 1, 2007.:)"Very true. I do not think my system has "broken down," it's just that it is underperforming at a dreadful level compared to how it had been. As for data range, I also stated it in reply to dingo but for some reason this system just rips apart 1999-2000 and 2000-2001 (1900% and 3700% CARs respectively) that I thought it was better to omit the two years and test after the dot-com bust. (yeah, 2000-2001 is technically including the bust but the system performs surprisingly well) I will once again optimize with 10 years of data and see how it goes. Thank you for your reply, intermilan04 --- In amibroker@yahoogroups.com, "sebastiandanconia" <[EMAIL PROTECTED]> wrote:Without knowing any more about your method (and I'm not asking), maybe there's nothing wrong and your system's performance is simply an accurate reflection of market action during those times? >From Jan.-Jan. in all those years there was a substantial movement (either up or down) in the overall stock market. Since January of this year, though, the markets have scarcely gone anywhere bycomparison.So, two things: First, the obvious one, you can't really know that your system has "broken down" until you get the final results on January 1, 2007.:) Second, if you believe that your system is based on actual market behaviors (not just randomly optimized) maybe it's working properly and this is just one of those years when nothing much happens. Which is why I believe that 8-10 years is pretty much the minimum necessary for an honest track record/backtest, rant, rant.:) This may be a totally valid "performance lull" period for a system that is stellar most of the time. Luck, Sebastian --- In amibroker@yahoogroups.com, "intermilan04" <intermilan04@> wrote:Hi all, I'm having a puzzling situation where my backtest results are fantastic yet my forwardtest result is nowhere near it. My system is optimized between 2001/1/1 and 2006/1/1. Results YTD is "forwardtest" since it is beyond the scope of optimized data range. Here are some numbers of backtests: Year-by-year-results (CAR) 2001/1/1-2002/1/1: 393.70% 2002/1/1-2003/1/1: 232.64% 2003/1/1-2004/1/1: 721.79% 2004/1/1-2005/1/1: 400.82% 2005/1/1-2006/1/1: 490.72% and at last--forwardtest 2006/1/1-2006/8/29: 74.64% I am at a loss to explain this. It's very sad that I work hard to come up with a system that has worked, only to see it not working nearly as good as it should be. Any analysis/suggestions to fix the problem above is greatlyappreciated.Sincerely, intermilan04Please note that this group is for discussion between users only. To get support from AmiBroker please send an e-mail directly to SUPPORT {at} amibroker.com For other support material please check also: http://www.amibroker.com/support.html Yahoo! Groups Links <*> To visit your group on the web, go to: http://groups.yahoo.com/group/amibroker/ <*> To unsubscribe from this group, send an email to: [EMAIL PROTECTED] <*> Your use of Yahoo! Groups is subject to: http://docs.yahoo.com/info/terms/ Please note that this group is for discussion between users only. To get support from AmiBroker please send an e-mail directly to SUPPORT {at} amibroker.com For other support material please check also: http://www.amibroker.com/support.html
SPONSORED LINKS
YAHOO! GROUPS LINKS
__,_._,___ |
- Re: [amibroker] Re: Backtest vs Forwardtest Herman
- [amibroker] Re: Backtest vs Forwardtest Fred
- [amibroker] Re: Backtest vs Forwardtest Fred
- [amibroker] Re: Backtest vs Forwardtest Fred
- [amibroker] Re: Backtest vs Forwardtest sebastiandanconia
- [amibroker] Re: Backtest vs Forwardtest intermilan04
- Re: [amibroker] Re: Backtest vs Forward... Dennis Brown
- [amibroker] Re: Backtest vs Forwar... intermilan04