arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2512.08591cs.LGcs.NE
收藏

长序列LSTM模型用于基于新型多赛季数据集的NBA比赛结果预测

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

University of Brighton(布莱顿大学)

Charles Rios, Longzhen Han, Almas Baimagambetov, Nikolaos Polatidis

AI总结:

本文提出了一种基于长序列LSTM模型的NBA比赛结果预测方法,利用新型多赛季数据集提升预测性能。

摘要:

预测专业篮球比赛的结果,特别是国家篮球协会(NBA)的比赛,对于教练策略、球迷参与和体育博彩变得越来越重要。然而,许多现有的预测模型在概念漂移、时间上下文有限和跨赛季不稳定方面存在困难。为了在该领域推进预测,我们介绍了一个新构建的纵向NBA数据集,涵盖2004-05至2024-25赛季,并提出了一种深度学习框架,旨在建模长期性能趋势。我们的主要贡献是一种长短期记忆(LSTM)架构,利用了9840场比赛的扩展序列长度,相当于八个完整的NBA赛季,以捕捉演变的球队动态和赛季间依赖性。我们比较了该模型与几种传统机器学习(ML)和深度学习(DL)基线模型,包括逻辑回归、随机森林、多层感知机(MLP)和卷积神经网络(CNN)。LSTM在所有指标上均取得最佳性能,准确率为72.35,精确率为73.15,AUC-ROC为76.13。这些结果展示了长期序列时间建模在篮球结果预测中的重要性,并突显了我们新多赛季数据集在开发稳健、可推广的NBA预测系统中的价值。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑