When interpretable machine learning meets the beautiful game: a predictive analytics approach to soccer player valuation in the transfer market
Bibliographic record
Abstract
Purpose The purpose of our research is to ascertain the key drivers of professional soccer player valuation in the transfer market. Design/methodology/approach Drawing on sports economics, finance and management literature, we connect data-driven approaches to player valuation in the context of organizational decision-making. We evaluate the performance of four predictive models using over 800 real-world transfer fee records and extensive features in the “Big Five” leagues from seasons 2017–2018 to 2019–2020. Subsequently, we leverage Shapley Additive Explanations (SHAP) values, an interpretable machine learning (ML) technique, to identify important features and quantify their contributions to transfer fees. Findings A few fundamental human capital factors (e.g. age) and labor market variables (e.g. contract remaining) emerge as the key value drivers, outweighing technical capabilities (e.g. goal-scoring). Sport-general features (e.g. composure and reaction) hold greater predictive power than soccer-specific skills (e.g. dribbling). Originality/value Our research enhances the explainability and transparency of a reasonably accurate player valuation model in two ways. First, we utilize a rich set of interpretable, fine-grained player features. Second and more importantly, SHAP values allow us to deconstruct player valuation and provide economic interpretations of feature importance at both individual and aggregate levels. We also outline the practical implications of adopting interpretable ML in sports organization decision-making.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".