Beyond the Expert: An Algorithmic Approach to Correcting Expert Bias in Fantasy Football Projections, authored by Vishnu Datta Jayanti, Allen High School, Allen, Texas.…Read More
Performance Analysis in the Brazilian Soccer League: Applying Machine Learning Techniques to Team Evaluation, authored by José Vinicius Boaventura Barbeiro, Universidade Tecnológica Federal do Paraná (UTFPR), Londrina, Brazil…Read More
All-Star Based Evaluation of Draft Value Curves Across Major North American Sports Leagues, authored by Jordan Abell, Latin School of Chicago, Felix Soloway-Gilbert, Pilgrim School, Jonathan Pipping-Gamón, University of Pennsylvania, and Abraham J. Wyner, University of Pennsylvania…Read More
With the Winter Olympics on the horizon, Penn students Trey Elder, Samen Hossain, and Jonathan Pipping break down the big strategy question in mixed doubles curling: when should teams deploy the Power Play? Their win-probability approach shows that the “right” moment isn’t just about points –– it’s about leverage.…Read More
With millions on the line every match, top soccer clubs still make critical substitution decisions based largely on intuition. This paper introduces an AI-powered Decision Support System (DSS) that brings data-driven rigor to one of the game’s most crucial tactical moments. Using fuzzy logic to model expert coaching knowledge, our system provides real-time substitution priorities by integrating validated performance metrics (playerankScore), fatigue (minutesPlayed), age, and disciplinary risk (TemCartaoAmarelo). A key innovation is its contextual logic, which modulates disciplinary risk based on a player’s tactical position (roleCluster), reflecting deeper tactical awareness. Validation through case studies confirms the system’s ability to balance conflicting factors and escalate priority in high-risk scenarios, providing a tangible competitive advantage for real-time game management when every decision counts.…Read More
A runner’s primary lead off first base creates leverage to steal second but also exposure to pickoffs. We develop a nested sequence of logistic models to estimate (i) pickoff attempts, (ii) pickoff success given an attempt, (iii) steal attempts given no pickoff, and (iv) steal success given an attempt, using 2024 MLB data and Baseball Savant metrics. We map stage probabilities to expected runs via fixed linear weights (+0.20 for a successful steal; -0.45 for caught stealing or picked off) and optimize over lead distance to obtain a context-specific optimal lead L ∗ . Empirically, observed leads are modestly larger than optimal on average (+0.19 ft), with a larger gap on steal attempts (+0.67), consistent with unobserved intent to steal. This framework quantifies the central trade-off – greater leads increase steal success but raise pickoff risk – on a common expected-runs scale and yield actionable, interpretable recommendations within the observed support.…Read More
Beyond Expected Goals (xG+) redefines how we measure scoring danger in soccer by valuing not just shots—but the moments that create them. By combining the probability of taking a shot with the chance of scoring it, xG+ captures players’ true creative impact, better predicts team performance, and finally gives credit for the skill that happens before the shot.…Read More
Research Note A Paradox of Blown Leads: Rethinking Win Probability in Football Authors: Jonathan Pipping, Ph.D. Student, Wharton Sports Analytics and Business Initiative Research Team Abraham J. Wyner, Faculty Co-Director, Wharton Sports Analytics and Business Initiative Published: July 4, 2025 Introduction Over the last 15 years, an explosion of publicly…Read More 
Research Note Introducing xCTRL: A Probabilistic Approach to Pitch Location Accuracy Authors: Matt Ludwig Ryan S. Brill, Ph.D., Wharton Sports Analytics and Business Initiative Research Team Abraham J. Wyner, Faculty Co-Director, Wharton Sports Analytics and Business Initiative Published: June 10, 2025 Traditional baseball metrics such as WHIP (walks plus hits…Read More
Research Note The Hall of Fame Cut in Major League Baseball Author: Shane T. Jensen, Professor of Statistics and Data Science, The Wharton School Published: January 22, 2025 1. Introduction In this paper, I create a new quantitative standard for the baseball Hall of Fame that is unambiguous while still…Read More 
