Walk-Off Labs

About

Our Mission

Walk-Off Labs builds products that help baseball teams turn data into actionable insights. We're a small group of engineers and academics with deep expertise in statistics, machine learning, and game theory.

The Problem We Solve

Every team in baseball has access to sophisticated matchup models and probability estimates. The tools exist. The data exists. But most teams aren't using them optimally.

Traditional approaches look at individual matchups in isolation. They tell you the probability of an outcome, but they don't tell you how to sequence decisions across an entire game to maximize your chances of winning.

Our Approach

We use game theory and Markov Decision Process (MDP) solvers to find optimal strategies. Instead of asking "what's the best play right now?", we ask "what sequence of decisions gives us the best chance to win the game?"

Our platform, Perfect Game, takes the Bayesian matchup models that teams are already using and finds the optimal way to act on them.

Our Team

Tristan Mott

Tristan Mott

Research Scientist

Brigham Young University

Tristan researches advanced statistical methods and machine learning applications for sports analytics.

Caleb Bradshaw

Caleb Bradshaw

Research Engineer

Walk-Off Labs

Caleb is a software engineer specializing in building systems that apply Walk-Off Labs' cutting edge research.

David Grimsman

David Grimsman

Professor of Computer Science

Brigham Young University

David has expertise in game theory and multi-agent systems.

Chris Archibald

Chris Archibald

Professor of Computer Science

Brigham Young University

Chris specializes in artificial intelligence, game playing, and decision making under uncertainty.