Flirting with Models cover image

Vivek Viswanathan - Quant Equity in China (S4E10)

Flirting with Models

CHAPTER

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.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner