Going Deep: Models for Continuous-TimeWithin-Play Valuation of Game Outcomesin American Football with Tracking Data

Continuous-time assessments of game outcomes in sports have become increasingly common in the last decade. In American football, only discrete-time estimates of play value were possible, since the most advanced public football datasets were recorded at the play-by-play level. While measures like expected points (EP) and win probability (WP) are useful for evaluating football plays and game situations, there has been no research into how these values change throughout a play. In this work, we make two main contributions: First, we introduce a general framework for continuous-time within-play valuation in the National Football League using player-tracking data. Our modular framework incorporates several modular sub-models, to easily incorporate recent work involving player tracking data in football. Second, we construct a ball-carrier model to estimate how many yards the ball-carrier will gain conditional on the locations and trajectories of all players. We test several modeling approaches, and ultimately use a long short-term memory recurrent neural network to continuously update the expected end-of-play yard line. This prediction is fed into between-play EP/WP models, yielding a within-play value estimate, but is adaptable to any measure of play value. The novel fully-implemented framework allows for continuous-time player evaluation.