I am looking for research papers which try to predict the market direction for a specific duration and have been successfully reproduced by people outside of the scientific community (so not just peer reviewed). According to jcl from financial-hacker.com, most papers in this domain are not reproducible (see http://www.financial-hacker.com/build-better-strategies-part-4-machine-learning/):
Every second week a new paper about trading with machine learning methods is published (a few can be found below). Please take all those publications with a grain of salt. According to some papers, phantastic win rates in the range of 70%, 80%, or even 85% have been achieved. Although win rate is not the only relevant criterion – you can lose even with a high win rate – 85% accuracy in predicting trades is normally equivalent to a profit factor above 5. With such a system the involved scientists should be billionaires meanwhile. Unfortunately I never managed to reproduce those win rates with the described method, and didn’t even come close. So maybe a lot of selection bias went into the results. Or maybe I’m just too stupid.
A commenter adds:
I have tried many machine learning techniques after reading various ‘peer reviewed’ papers. But reproducing their results remains elusive. When I live test with ML I can’t seem to outperform random entry.
An accuracy of 55% would already be more than enough for me. I am especially interested in machine learning classifiers which return a probability.
Any suggestions for such papers?
Submitted October 10, 2018 at 01:28PM by kalabele
via https://ift.tt/2pJPbp7
Stock Trading NTS 