Machine Learning Applications in Sport: A Scoping Review of 270 Studies

270 peer-reviewed studies on machine learning in sport, published between 2002 and 2024, were analyzed in this scoping review. The author, Antonia Cattle, examined applications across 12 subject areas, with computer science, biomechanics, and sport psychology being the most common. The review discusses key applications like action recognition and injury prediction, while noting limitations in data quality and model interpretability.

Use Cases

• Survey the landscape of ML research in sport based on the analysis of 270 studies.
• Identify common application domains like action recognition and injury prediction based on the review's findings.
• Understand limitations to practical ML deployment in sport based on the described issues of data quality and interpretability.

Strengths

• Analyzes a substantial corpus of 270 peer-reviewed studies.
• Covers a long temporal range from 2002 to 2024.
• Explicitly licensed under CC-BY-4.0 for open sharing and reuse.

Limitations

• The dataset is a 19.3 KB DOCX file, indicating a very limited scope, likely a summary document rather than raw data.
• Row count and column-level documentation are absent; the file's internal structure must be inspected after download.
• The description is general; specific data points, models, or performance metrics from the reviewed studies are not provided.

Provenance

Source

figshare

Collection Method

Scoping review of academic literature.

Time Range

2002 to 2024

Freshness

Last updated 2026-05-25 06:04:52.