Welcome
Issue One Hundred And Fifty Eight.
These articles cover various sports analytics topics, including a Bayesian model to estimate peak home run ability, a betting strategy exploiting odds inefficiencies, and the role of randomness in soccer. They also introduce a metric to measure substitution impact in football and a tool to visualize passing patterns using open soccer data.
This Week's Lineup
Exploring Peak Home Run Rates Using a Multilevel Model
This article introduces a multilevel Bayesian model to estimate a hitter's peak home run ability and the age at which it occurs, applying the model to members of the 400 career home run club and illustrating it with an analysis of Mickey Mantle's career.
Beating the bookies with their own numbers
This study developed a profitable betting strategy by exploiting mispriced odds in the football betting market, demonstrating through simulations and real-life betting that bookmakers can be consistently beaten, though they compensate for market inefficiencies by discriminating against successful bettors.
On Randomness (and Parity)
explores the concept of randomness in soccer, discussing how the frequency of shots and goals, team risk appetite, and game structure contribute to unpredictable outcomes, with randomness being both an obstacle to understanding through analytics and an inherent part of the game that managers must strategically manage.
Expected Impact: A New Way to Measure Substitutions
Introducing "Expected Impact" (xI), a metric that quantifies the influence of a substitution on team performance, helping managers make more informed, data-driven decisions when choosing substitutes.
A football/soccer pass visualizer made with Three.js
It uses open data from StatsBomb to analyse and visualise passing patterns, allowing users to explore and filter the data by pass distance, team and players.
Please Forward
Was this email forwarded to you? Sign up here >>
Unexpected Points Added is curated and maintained by Patrick Hayes.
I completed a Master of Applied Data Science from the University of Michigan; let's connect.
Send me an email with your feedback or questions. I respond to every single one.