Gaining Momentum: Uncovering Hidden Scoring Dynamics in Hockey through Deep Neural Sequencing and Causal Modeling

TL;DR

This paper introduces a comprehensive data-driven framework that combines machine learning and causal inference to identify and quantify tactical sequences and formations that causally improve scoring chances in professional hockey.

Contribution

It presents a novel integrated pipeline using deep learning, statistical modeling, and causal inference to uncover and quantify the impact of specific game strategies on scoring outcomes.

Findings

Identified sequences and formations that causally increase scoring likelihood.

Achieved a 15% relative gain in offensive scoring potential.

Demonstrated real-time tactical insights for hockey coaching and analysis.

Abstract

We present a unified, data-driven framework for quantifying and enhancing offensive momentum and scoring likelihood (expected goals, xG) in professional hockey. Leveraging a Sportlogiq dataset of 541,000 NHL event records, our end-to-end pipeline comprises five stages: (1) interpretable momentum weighting of micro-events via logistic regression; (2) nonlinear xG estimation using gradient-boosted decision trees; (3) temporal sequence modeling with Long Short-Term Memory (LSTM) networks; (4) spatial formation discovery through principal component analysis (PCA) followed by K-Means clustering on standardized player coordinates; and (5) use of an X-Learner causal inference estimator to quantify the average treatment effect (ATE) of adopting the identified "optimal" event sequences and formations. We observe an ATE of 0.12 (95% CI: 0.05-0.17, p < 1e-50), corresponding to a 15% relative gain in scoring potential. These results demonstrate that strategically structured sequences and compact formations causally elevate offensive performance. Our framework delivers real-time, actionable insights for coaches and analysts, advancing hockey analytics toward principled, causally grounded tactical optimization.