Good evening,
I just implemented a filter in my pipeline so that when I filter my universe of stocks in my pipeline, it picks only those with the highest P/E ratio. The idea was that if the P/E ratio is high the stock might be more of a temporary "fad" and by consequence more exposed to the strategy written here in this paper: http://www.sciencedirect.com/science/article/pii/S1059056016301563
Unfortunately the result is not super exciting since the Sharpe ratio is pretty low; moreover, while the algo performs really well in the crisis, it seems do stop/decrease in growth during the recovery and I don't really understand why since the beta is always close to zero. Is there any mistake that I might be doing? Do you have any suggestion on how to improve my code? Or on other fundamentals/indicators that I could consider?
Thanks a lot in advance,
Mattia