Long-Sequence LSTM Modeling for NBA Game Outcome Prediction Using a Novel Multi-Season Dataset
This work addresses concept drift and temporal limitations in sports prediction for coaching, fan engagement, and betting, though it is incremental as it applies an existing LSTM method to a new dataset.
The paper tackled the problem of predicting NBA game outcomes by introducing a new multi-season dataset and a long-sequence LSTM model, achieving 72.35% accuracy and 76.13 AUC-ROC, which outperformed traditional baselines.
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.