Long-Sequence LSTM Modeling for NBA Game Outcome Prediction Using a Novel Multi-Season Dataset

TL;DR

This paper introduces a long-sequence LSTM model trained on a comprehensive multi-season NBA dataset, significantly improving game outcome prediction accuracy by capturing long-term team performance trends and season dependencies.

Contribution

The paper presents a novel LSTM architecture that models extended game sequences over multiple seasons, addressing concept drift and temporal context limitations in NBA outcome prediction.

Findings

LSTM outperforms traditional ML and DL models in accuracy and AUC-ROC.

Extended sequence modeling captures evolving team dynamics effectively.

New multi-season dataset enables more robust and generalizable predictions.

Abstract

Predicting the outcomes of professional basketball games, particularly in the National Basketball Association (NBA), has become increasingly important for coaching strategy, fan engagement, and sports betting. However, many existing prediction models struggle with concept drift, limited temporal context, and instability across seasons. To advance forecasting in this domain, we introduce a newly constructed longitudinal NBA dataset covering the 2004-05 to 2024-25 seasons and present a deep learning framework designed to model long-term performance trends. Our primary contribution is a Long Short-Term Memory (LSTM) architecture that leverages an extended sequence length of 9,840 games equivalent to eight full NBA seasons to capture evolving team dynamics and season-over-season dependencies. We compare this model against several traditional Machine Learning (ML) and Deep Learning (DL) baselines, including Logistic Regression, Random Forest, Multi-Layer Perceptron (MLP), and Convolutional Neural Network (CNN). The LSTM achieves the best performance across all metrics, with 72.35 accuracy, 73.15 precision and 76.13 AUC-ROC. These results demonstrate the importance of long-sequence temporal modeling in basketball outcome prediction and highlight the value of our new multi-season dataset for developing robust, generalizable NBA forecasting systems.