{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T06:04:17Z","timestamp":1790229857506,"version":"4.1.0"},"reference-count":14,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T00:00:00Z","timestamp":1790208000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Horse-racing prediction was used as a case study to develop and evaluate a leakage-aware machine-learning framework based on information available after race-entry finalization and before outcomes were known. Japanese Racing Association flat-race data obtained through JRA-VAN Data Lab. and exported using TARGET frontier JV were split temporally: 2015\u20132022 for training, 2023\u20132024 for validation, and January 5, 2025 to May 10, 2026 for independent testing. The test set contained 63,910 horse-level observations from 4,556 races. Confidence intervals were estimated using 10,000 race-level bootstrap resamples. Two horse-level binary outcome labels were evaluated: a win outcome and a JRA place-rule-compatible place outcome derived from the processed field_size variable. Compared with the augmented current_full_model, the hyperparameter-matched no-theory sensitivity-analysis model matched_no_theory_model performed better for both outcomes. For the win outcome, ROC AUC was 0.7543 (95% CI: 0.7475\u20130.7609) for matched_no_theory_model and 0.7293 (95% CI: 0.7224\u20130.7362) for current_full_model. For the JRA place-rule-compatible place outcome, ROC AUC was 0.7513 (95% CI: 0.7469\u20130.7558) and 0.7164 (95% CI: 0.7118\u20130.7212), respectively. An exploratory race-level uncertainty diagnostic was evaluated separately and was not incorporated into the horse-level prediction models. These findings indicate that the evaluated theory-score block did not improve temporal test-set performance. Domain-derived feature blocks should be evaluated incrementally through leakage audits, temporal validation, feature-block ablation, and matched sensitivity analyses before deployment.<\/jats:p>","DOI":"10.3389\/frai.2026.1896192","type":"journal-article","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T05:43:23Z","timestamp":1790228603000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Leakage-aware pre-event machine learning evaluation for horse-race prediction under temporal validation"],"prefix":"10.3389","volume":"9","author":[{"given":"Shuichi","family":"Sugiura","sequence":"first","affiliation":[{"name":"Graduate School of Psychology, Kansai University","place":["Suita, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,24]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1186\/s13104-022-06082-4","article-title":"Reproducibility of prediction models in health services research","volume":"15","author":"Belbasis","year":"2022","journal-title":"BMC Res. Notes"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1040","DOI":"10.1287\/mnsc.32.8.1040","article-title":"Searching for positive returns at the track: a multinomial logit model for handicapping horse races","volume":"32","author":"Bolton","year":"1986","journal-title":"Manage. Sci"},{"key":"B3","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.aci.2017.09.005","article-title":"A machine learning framework for sport result prediction","volume":"15","author":"Bunker","year":"2019","journal-title":"Appl. Comput. Inf."},{"key":"B4","doi-asserted-by":"publisher","first-page":"e078378","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"B5","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1198\/016214506000001437","article-title":"Strictly proper scoring rules, prediction, and estimation","volume":"102","author":"Gneiting","year":"2007","journal-title":"J. Am. Stat. Assoc"},{"key":"B6","first-page":"1157","article-title":"An introduction to variable and feature selection","volume":"3","author":"Guyon","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"B7","doi-asserted-by":"publisher","first-page":"e1380","DOI":"10.1002\/widm.1380","article-title":"The use of machine learning in sport outcome prediction: a review","volume":"10","author":"Horvat","year":"2020","journal-title":"WIREs Data Mining Knowl. Disc."},{"key":"B8","unstructured":"Place betting rule information\n          \n          2026"},{"key":"B9","unstructured":"JRA-VAN Data Lab\n          \n          2026"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2382577.2382579","article-title":"Leakage in data mining: Formulation, detection, and avoidance","volume":"6","author":"Kaufman","year":"2012","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"B11","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1016\/j.ejor.2008.03.018","article-title":"Identifying winners of competitive events: a SVM-based classification model for horserace prediction","volume":"196","author":"Lessmann","year":"2009","journal-title":"Eur. J. Oper. Res"},{"key":"B12","unstructured":"Scikit-learn: Machine Learning in Python\n          \n          2825\n          2830\n          \n            \n              Pedregosa\n              F.\n            \n            \n              Varoquaux\n              G.\n            \n            \n              Gramfort\n              A.\n            \n            \n              Michel\n              V.\n            \n            \n              Thirion\n              B.\n            \n            \n              Grisel\n              O.\n            \n          \n          J. Mach. Learn. Res.\n          12\n          2011"},{"key":"B13","doi-asserted-by":"publisher","first-page":"913","DOI":"10.1111\/ecog.02881","article-title":"Cross-validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure","volume":"40","author":"Roberts","year":"2017","journal-title":"Ecography"},{"key":"B14","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1002\/hcs2.114","article-title":"Toward real-world deployment of machine learning for health care: External validation, continual monitoring, and randomized clinical trials","volume":"3","author":"Yuan","year":"2024","journal-title":"Health Care Sci."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1896192\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T05:43:24Z","timestamp":1790228604000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1896192\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,24]]},"references-count":14,"alternative-id":["10.3389\/frai.2026.1896192"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1896192","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,24]]},"article-number":"1896192"}}