In our new paper https://t.co/uwAtDIaJwu , @skdeshpande91 and I develop a framework for estimating the optimal swing decision of batters in Major League Baseball. We take a Bayesian approach to estimating the expected runs following a swing and take decision. (5/7)
🚨 SIGNED GIVEAWAY 🚨
To win:
1. RT
2. Comment #ProBowlVote + [any Packers player name]
Christian Watson
Jordan Love
Zach Tom
Daniel Whelan
Romeo Doubs
Rasheed Walker
Sean Rhyan
Evan Williams
Isaiah McDuffie
Luke Musgrave
Join me at the SBSS Student Paper Award I session from 10:30 AM to 12:20 PM. A special thanks to my co-authors Soham Ghosh and Sameer Deshpande for their help on this project!
Paper for the details: https://t.co/FTQNS7Gws5
R package: https://t.co/6fiYJjsdvt
Giving a talk at JSM tomorrow on ridgeBART!
This is a game-changer for sports analytics. Our method opens up new possibilities for modeling complex spatial data on large datasets, allowing us to tackle problems that simply weren't possible before with tree-based models.
I'll be discussing the details of the method and demonstrating its capabilities on an NBA shot dataset.
As a preview, here is a comparison of FG% estimates by BART and ridgeBART for Stephen Curry:
Two thoughts: i) the way you use the tool matters, creativity and ingenuity continue to be rewarded; ii) demand for inference-time compute will continue to grow exponentially https://t.co/0NiMsbeeHY
I was talking to someone who works in real estate this weekend. He said discount rates on commercial properties are typically 10-20% but currently closer to 20-30%. Meanwhile, discount rates on residential are <10%, with a point estimate around 5%. Seems like a big opportunity.
Using our framework, teams can identify batters who consistently make optimal swing decisions and identify situations and pitch locations where specific batters tend to make sub-optimal decisions. These analyses can be conducted using our shiny app: https://t.co/p41l7G10md (7/7)
The notion of plate discipline in baseball refers to the idea that batters should be selective in the pitches they choose to swing at. Given this principle, the question arises: how should batters determine which pitches are worth a swing? (1/7)