My Random Forest Was Mostly Learning Time-to-Expiry Noise
illya.shThe blogger trained a random forest on the returns of some price with a set of features and the ttm feature was strongest. Did I miss anything?
What's the context? I feel like there's at least three paragraphs of intro missing here.
If you scroll past the posts about oil, you will find dozens of posts on the same subject (mentioning random forests).
It seems to be predicting Bitcoin price.
Edit: this seems to be the most detailed post:
https://illya.sh/thoughts/my-trading-ml-factory-yielded-22-r...
Why not use SHAP?
That's a refreshing article. Easy to read and I learned a few things!