Name
Uncovering Causal Relationships in Sports Analytics: Methods and Applications
Date & Time
Friday, April 11, 2025, 1:00 PM - 2:10 PM
Description
In this workshop, we will introduce the fundamentals of causal inference, including the potential outcomes framework and causal discovery, emphasizing the importance of causality in sports analytics. We will apply these concepts to NBA data to address specific challenges and uncover actionable insights. The workshop will also explore recent advancements in causal machine learning techniques, such as meta-learners and causal discovery with temporal ordering.
Session Type
Workshop
Title
Uncovering Causal Relationships in Sports Analytics: Methods and Applications
Abstract
In this workshop, we will introduce the fundamentals of causal inference, including the potential outcomes framework and causal discovery, emphasizing the importance of causality in sports analytics. We will apply these concepts to NBA data to address specific challenges and uncover actionable insights. The workshop will also explore recent advancements in causal machine learning techniques, such as meta-learners and causal discovery with temporal ordering.
Prerequisites: Familiarity with R and Python.
Prerequisites: Familiarity with R and Python.
Speaker Bio
Shinpei Nakamura-Sakai is a Ph.D. candidate in Statistics and Data Science at Yale University. His research in sports analytics introduces a framework for analyzing age curves to examine how factors like rest days impact athlete performance across career stages. Shinpei has industry experience as a quantitative analytics associate at JPMorgan Chase and an applied scientist at Amazon, and he has won Best Poster Awards at both UCSAS 2022 and NESSIS 2023.
Speaker Headshot
