AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
How to Explain Under Performance in a Machine Learning Environment
The last type of factor timing that i've seen is regime switzing models. I personally have not seen this work in contests of timi they can build amazing back tests, but seem to turn into random number generators ex post. Most regime switching models i see are 90 % confident there in one regime or the other. And then you infer conditional expect o returns based on those regime states. They're way to over confident, and thus they can result in bad decision make.