{"id":"W4416177431","doi":"10.1108/sbm-05-2025-0108","title":"When interpretable machine learning meets the beautiful game: a predictive analytics approach to soccer player valuation in the transfer market","year":2025,"lang":"en","type":"article","venue":"Sport Business and Management An International Journal","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brock University","funders":"","keywords":"Valuation (finance); Leverage (statistics); Predictive power; Predictive analytics; Transfer of learning; Transparency (behavior); Business valuation; Analytics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001581469,0.0001359549,0.0001935061,0.0004678921,0.000160051,0.0004319581,0.0004989065,0.00003918192,0.0002374125],"category_scores_gemma":[0.0000150453,0.00009565928,0.00006121286,0.0003290078,0.00003640537,0.0004076143,0.00008182663,0.000247962,0.000004612031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007914205,"about_ca_system_score_gemma":0.00001727544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002457095,"about_ca_topic_score_gemma":0.00009600748,"domain_scores_codex":[0.9989086,0.00001448774,0.0004856658,0.0002529525,0.0001596113,0.0001786997],"domain_scores_gemma":[0.999541,0.00001331,0.0001296826,0.0001590734,0.000121355,0.00003553562],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004890335,0.0004281558,0.4833046,0.00006478884,0.0007703395,0.00003916168,0.004558695,0.06495649,9.574673e-7,0.4322975,0.003576178,0.009514028],"study_design_scores_gemma":[0.0005274486,0.00002785947,0.598739,0.00005648069,0.00004306364,0.00001330565,0.0005439773,0.2546006,4.278858e-7,0.007469841,0.137852,0.0001260335],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.424222,0.001309195,0.3746696,0.01854749,0.001918881,0.001152712,0.00007287352,0.00003264951,0.1780746],"genre_scores_gemma":[0.9930985,0.001765161,0.000222255,0.001403783,0.0001367996,0.0000322715,0.00003978274,0.00001006478,0.003291365],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5688765,"threshold_uncertainty_score":0.4165382,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02319406649935193,"score_gpt":0.2405320702119616,"score_spread":0.2173380037126097,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}