Learning Bayesian Statistics cover image

#49 The Present & Future of Baseball Analytics, with Ehsan Bokhari

Learning Bayesian Statistics

CHAPTER

Is There a Trade-Off Between Interpretability and Accuracy?

We often have a trade off with interpretability and accuracy. So being able to provide tools like that can go a long way, so that that whoever's using it, whether it be the coaches or the scouts,. Though, we provide them to get a better understanding of ok for instance, we if thi player increases his velocity by one mile per hour, what does that look like for his what we call pitch grade, how good his pitches are? And so building those tools can really help. Even if the model itself isn't directly interpretable, those type of tools can make it interpretable to some extent. But i think one of the more difficult things to explain are inner actions.

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