Predicting Volleyball Season Performance Using Pre-Season Wearable Data and Machine Learning

2025-03-11

AI Summary

This study aims to predict in-season performance of collegiate volleyball athletes using preseason wearable-device data, enabling early identification of high- versus low-performing individuals. Methodologically, it introduces the first integration of passive physiological signals from smartwatches—such as heart rate variability and physical activity—with ecologically valid subjective psychological states captured via ecological momentary assessment (EMA), forming a multimodal, day-level feature set. An integrated feature engineering pipeline coupled with machine learning modeling is employed, and model performance is rigorously evaluated using leave-one-subject-out (LOSO) cross-validation. The resulting model achieves an F1-score of 0.75, significantly outperforming unimodal baselines. Key contributions include: (1) pioneering the synergistic use of objective wearable metrics and dynamic self-reported states for personalized pre-competition performance prediction; (2) identifying critical cross-dimensional predictive factors—e.g., the interaction between nocturnal recovery quality and pre-competition anxiety; and (3) delivering an interpretable, deployable framework supporting day-level targeted interventions.

Technology Category

• Intelligent Robots: State Estimation
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Hardware-aware ML

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Large-scale security measurements

Abstract

Predicting performance outcomes has the potential to transform training approaches, inform coaching strategies, and deepen our understanding of the factors that contribute to athletic success. Traditional non-automated data analysis in sports are often difficult to scale. To address this gap, this study analyzes factors influencing athletic performance by leveraging passively collected sensor data from smartwatches and ecological momentary assessments (EMA). The study aims to differentiate between 14 collegiate volleyball players who go on to perform well or poorly, using data collected prior to the beginning of the season. This is achieved through an integrated feature set creation approach. The model, validated using leave-one-subject-out cross-validation, achieved promising predictive performance (F1 score = 0.75). Importantly, by utilizing data collected before the season starts, our approach offers an opportunity for players predicted to perform poorly to improve their projected outcomes through targeted interventions by virtue of daily model predictions. The findings from this study not only demonstrate the potential of machine learning in sports performance prediction but also shed light on key features along with subjective psycho-physiological states that are predictive of, or associated with, athletic success.

Problem

• Predict volleyball performance using pre-season wearable data.
• Differentiate players' future performance via machine learning models.
• Enable targeted interventions based on predictive performance insights.

Innovation

• Leverages wearable smartwatch data for performance prediction
• Uses machine learning with ecological momentary assessments
• Predicts athlete performance using pre-season data