Department of Physical Therapy and Human Movement Science, Sacred Heart University, Fairfield, CT, USA.
School of Engineering and Applied Science, Ahmedabad University, Ahmedabad, Gujarat, India.
Sci Rep. 2024 Jan 12;14(1):1162. doi: 10.1038/s41598-024-51658-8.
Predictive sports data analytics can be revolutionary for sports performance. Existing literature discusses players' or teams' performance, independently or in tandem. Using Machine Learning (ML), this paper aims to holistically evaluate player-, team-, and conference (season)-level performances in Division-1 Women's basketball. The players were monitored and tested through a full competitive year. The performance was quantified at the player level using the reactive strength index modified (RSImod), at the team level by the game score (GS) metric, and finally at the conference level through Player Efficiency Rating (PER). The data includes parameters from training, subjective stress, sleep, and recovery (WHOOP straps), in-game statistics (Polar monitors), and countermovement jumps. We used data balancing techniques and an Extreme Gradient Boosting (XGB) classifier to predict RSI and GS with greater than 90% accuracy and a 0.9 F1 score. The XGB regressor predicted PER with an MSE of 0.026 and an R of 0.680. Ensemble of Random Forest, XGB, and correlation finds feature importance at all levels. We used Partial Dependence Plots to understand the impact of each feature on the target variable. Quantifying and predicting performance at all levels will allow coaches to monitor athlete readiness and help improve training.
预测性体育数据分析对于体育表现可能具有革命性的意义。现有文献讨论了球员或球队的表现，无论是独立的还是联合的。本文使用机器学习（ML），旨在全面评估一级女子篮球中球员、球队和会议（赛季）级别的表现。通过一个完整的竞争年度对球员进行监测和测试。在球员层面上，使用反应强度指数修正（RSImod）来量化表现，在球队层面上使用比赛得分（GS）指标，最后在会议层面上通过球员效率评级（PER）进行量化。数据包括来自训练、主观压力、睡眠和恢复（WHOOP 表带）、比赛中的统计数据（Polar 监测器）和下蹲跳的数据。我们使用数据平衡技术和极端梯度提升（XGB）分类器，以超过 90%的准确率和 0.9 的 F1 分数预测 RSI 和 GS。XGB 回归器以 0.026 的均方误差和 0.680 的 R 预测 PER。随机森林、XGB 和相关性的集成在所有级别上都找到了特征的重要性。我们使用部分依赖图来了解每个特征对目标变量的影响。在所有级别上量化和预测表现将使教练能够监测运动员的准备情况，并有助于改进训练。
