Abstract
Background
Accurate evaluation of non-professional padel players is essential for optimizing training and ensuring fair competition. Traditional result-based ranking systems, often reliant on self-assessment, can be biased. In contrast, AI-driven methods utilizing computer vision and deep learning promise objective, real-time performance evaluations.
Methods
In this study, evaluation scores for 180 players were derived from three sources: a self-assessed result-based system (Playtomic), an AI-based system (AIball), and expert coach assessments, which served as the benchmark. AIball is a computer-vision–based evaluation system that automatically extracts key performance metrics. Data were collected from 50 matches across 9 clubs in Spain. Statistical analyses—including Pearson correlation, Intraclass Correlation Coefficient (ICC), Lin's Concordance Correlation Coefficient (CCC), paired t-tests, Bland-Altman analysis, and error metrics (mean squared error [MSE], root mean squared error [RMSE], and mean absolute error [MAE])—were employed to assess the reliability, agreement, and classification accuracy of the evaluation systems.
Results
AIball demonstrated a strong positive correlation with coach evaluations (r = 0.7769; CCC = 0.7144) and yielded lower error metrics (MSE = 0.6689; RMSE = 0.8178; MAE = 0.6678) compared to Playtomic. Bland-Altman plots revealed that AIball's scores were more closely aligned with those of the experts, and pairwise comparisons showed a slightly higher classification accuracy for AIball (74.27%) relative to Playtomic (73.74%).
Conclusion
The findings indicate that the AI-based evaluation system (AIball) offers a more reliable and objective assessment of non-professional padel players than traditional self-assessed methods. This approach has significant implications for enhancing training programs, standardizing player rankings, and promoting fairness in competitions.
Get full access to this article
View all access options for this article.