Will artificial intelligence solve the riddle of athlete development? A critical review of how AI is being used for athlete identification, selection, and development
Bibliographic record
Abstract
The last decade has seen a rapid increase in the use of artificial intelligence (AI) approaches such as machine learning and deep learning in the sport sciences. However, despite the increased interest in this area, the scope and utility of, and challenges associated with, these approaches are relatively unknown. This critical review aimed to scan sport science research for articles using AI in athlete development contexts (i.e., talent/athlete identification, talent/athlete selection, and talent/athlete development). Through database, external reference lists, book chapters, and other relevant resource searching, information from eligible articles was extracted and form the basis of the current review. The use of AI was prominent in three main areas: improving athlete assessment, athlete selection and classification, and athlete development and training. These technologies have been used in a variety of ways and appear to have potential value for those working in this area. The challenges associated with these approaches are also discussed. AI in the context of athlete development allows for access to more data, more easily, and with greater statistical complexity, than ever before. Importantly, a balanced approach that embraces both innovation and critical evaluation seems necessary to ensure these tools enhance, rather than disrupt, the athlete identification, selection, and development landscape. • Sport science has seen a rapid emergence in technologies such as artificial intelligence, deep-learning, and machine learning. • This review critically evaluates the use of artificial intelligence in athlete development contexts. • Research to date suggests value in the use of these technologies in athlete development settings, although there are unique challenges. • An approach embracing both innovation and critical evaluation will ensure these tools enhande, rather than disrupt, athlete development
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.016 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.004 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.004 | 0.005 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".