Solas, how long does it take to do 137 stocks? Have you upgraded to a solution with multiple runs of the program? The software has been doing well and I'm satisfied but I'd like to decrease time it takes to output the results. I run it with 200 stocks at this stage.
This one looks interesting and in trying a demo seems quite accurate. I purchased another program from same company years ago and that was also interesting but due to new job I didn't devote any time and license expired.
Has anyone tried the DQ option? Any ideas in general?
Interesting software. have you tried it in actual trading? What features are you using for classification? I think success depends on features. Have you tried long-short strategies as in this article?
I think DLPAL is selling the features more than the software. I am now trying the demo and...
OK - so you say it is not. Just tell me where the mark-to-market gains of winners come daily after market close if not from the mark-to-market losses of the losers. Is anyone paying the winners besides the losers? If not, it is a zero-sum.
The article is interesting in many aspects, not only about the comparison but also about the points made regarding calculation of performance figures. I think it is useful read.
Paper trading has exactly the same problems with backtesting since market dynamics can change immediately after you are convinced that you have a sound strategy. This paper in ssrn has in it two examples that demonstrate this problem. http://papers.ssrn.com/sol3/papers.cfm?abstract_id=2810170
Machine learning is supposed to do that but it seems it also hasn't been successful as the numeral results indicate.
http://www.trade2win.com/boards/general-trading-chat/218380-numerai-new-post.html