Hey GAT, Is it a good use of time to try to build a more accurate trend filter? Say using machine learning techniques and using more factors/features to redue noise/detection? If not why so?
No, a bad use of time IMHO. I'd be surprised if you could get significantly better out of sample performance from the ragtag bunch of simple trend rules I use myself (I've seen people try, and fail, at this). You're better off diversifying your system to different instruments and different styles of trading. GAT
Hi GAT, I know you mentioned that trading rules that are too fast can be excluded due to costs. Let's assume that costs are low or near 0. Is there a timescale at which momentum effect is overwhelmed by noise such that it is useless as a trading rule?