{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T23:13:44Z","timestamp":1777590824507,"version":"3.51.4"},"reference-count":62,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2024,3,4]],"date-time":"2024-03-04T00:00:00Z","timestamp":1709510400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Sylvan Adams Family Foundation Israel"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Professional bicycle racing is a popular sport that has attracted significant attention in recent years. The evolution and ubiquitous use of sensors allow cyclists to measure many metrics including power, heart rate, speed, cadence, and more in training and racing. In this paper we explore for the first time assignment of a subset of a team\u2019s cyclists to an upcoming race. We introduce RaceFit, a model that recommends, based on recent workouts and past assignments, cyclists for participation in an upcoming race. RaceFit consists of binary classifiers that are trained on pairs of a cyclist and a race, described by their relevant properties (features) such as the cyclist\u2019s demographic properties, as well as features extracted from his workout data from recent weeks; as well additional properties of the race, such as its distance, elevation gain, and more. Two main approaches are introduced in recommending on each stage in a race and aggregate from it to the race, or on the entire race. The model training is based on binary label which represent participation of cyclist in a race (or in a stage) in past events. We evaluated RaceFit rigorously on a large dataset of three pro-cycling teams\u2019 cyclists and race data achieving up to 80% precision@i. The first experiment had shown that using TP or STRAVA data performs the same. Then the best-performing parameters of the framework are using 5 weeks time window, imputation was effective, and the CatBoost classifier performed best. However, the model with any of the parameters performed always better than the baselines, in which the cyclists are assigned based on their popularity in historical data. Additionally, we present the top-ranked predictive features.<\/jats:p>","DOI":"10.1371\/journal.pone.0297270","type":"journal-article","created":{"date-parts":[[2024,3,4]],"date-time":"2024-03-04T18:21:57Z","timestamp":1709576517000},"page":"e0297270","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":9,"title":["Pro-cycling team cyclist assignment for an upcoming race"],"prefix":"10.1371","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9771-959X","authenticated-orcid":true,"given":"Maor","family":"Sagi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paulo","family":"Saldanha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guy","family":"Shani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Moskovitch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2024,3,4]]},"reference":[{"key":"pone.0297270.ref001","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1007\/978-3-319-22312-4_2","volume-title":"The Economics of Professional Road Cycling","author":"JF Mignot","year":"2016"},{"key":"pone.0297270.ref002","unstructured":"Sagi M, Saldanha P, Shani G, Moskovitch R. In: ECML PKDD 2022 Workshop on Machine Learning and Data Mining for Sports Analytics; 2022."},{"key":"pone.0297270.ref003","unstructured":"Internationale UC. UCI Cycling Regulations Part I\u2014General Organisation of Cycling as a Sport; 2022. Available from: https:\/\/assets.ctfassets.net\/761l7gh5x5an\/wQympSG6EWlKq6o6HKw9E\/d4f7039ce3bf3963b457ae35cf5449bd\/1-GEN-20220301-E.pdf."},{"key":"pone.0297270.ref004","unstructured":"Internationale UC. UCI Cycling Regulations Part II\u2014Road Races; 2022. Available from: https:\/\/assets.ctfassets.net\/761l7gh5x5an\/7MLz0Fo06hpqNvEvrlXaf2\/b5ffbf462d47f4d559d90d2089d128ae\/2-ROA-20220401-E.pdf."},{"key":"pone.0297270.ref005","unstructured":"Training Peaks Fitness App. Available from: https:\/\/www.trainingpeaks.com."},{"key":"pone.0297270.ref006","unstructured":"STRAVA Running, Cycling & Hiking App. Available from: https:\/\/www.strava.com."},{"key":"pone.0297270.ref007","unstructured":"Pro Cycling Stats Cycling Statistics, Results, and Rankings Website. Available from: https:\/\/www.procyclingstats.com."},{"issue":"1","key":"pone.0297270.ref008","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1249\/01.mss.0000183196.63081.6a","article-title":"Power output during stage racing in professional road cycling","volume":"38","author":"S Vogt","year":"2006","journal-title":"Medicine & Science in Sports & Exercise"},{"issue":"12","key":"pone.0297270.ref009","doi-asserted-by":"crossref","first-page":"1299","DOI":"10.1080\/02640410601001632","article-title":"Cycling power output produced during flat and mountain stages in the Giro d\u2019Italia: a case study","volume":"25","author":"S Vogt","year":"2007","journal-title":"Journal of Sports Sciences"},{"key":"pone.0297270.ref010","article-title":"Training characteristics of male and female professional road cyclists: a four-year retrospective analysis","author":"T Erp","year":"2019","journal-title":"International Journal of Sports Physiology and Performance"},{"issue":"5","key":"pone.0297270.ref011","doi-asserted-by":"crossref","first-page":"872","DOI":"10.1249\/01.MSS.0000064999.82036.B4","article-title":"Tour de France versus Vuelta a Espana: Which is harder?","volume":"35","author":"A Luc\u00eda","year":"2003","journal-title":"Medicine & Science in Sports & Exercise"},{"issue":"10","key":"pone.0297270.ref012","doi-asserted-by":"crossref","first-page":"1348","DOI":"10.1123\/ijspp.2016-0294","article-title":"Decrement in professional cyclists\u2019 performance after a grand tour","volume":"12","author":"JA Rodr\u00edguez-Marroyo","year":"2017","journal-title":"International Journal of Sports Physiology and Performance"},{"issue":"12","key":"pone.0297270.ref013","doi-asserted-by":"crossref","first-page":"1385","DOI":"10.1080\/02640414.2017.1388669","article-title":"Analysing a cycling grand tour: Can we monitor fatigue with intensity or load ratios?","volume":"36","author":"D Sanders","year":"2018","journal-title":"Journal of Sports Sciences"},{"issue":"6","key":"pone.0297270.ref014","doi-asserted-by":"crossref","first-page":"736","DOI":"10.1080\/17461391.2018.1554706","article-title":"Physical demands and power profile of different stage types within a cycling grand tour","volume":"19","author":"D Sanders","year":"2019","journal-title":"European Journal of Sport Science"},{"issue":"4","key":"pone.0297270.ref015","doi-asserted-by":"crossref","first-page":"868","DOI":"10.1249\/MSS.0000000000002210","article-title":"Case report: load, intensity, and performance characteristics in multiple grand tours","volume":"52","author":"T Van Erp","year":"2020","journal-title":"Medicine & Science in Sports & Exercise"},{"issue":"5","key":"pone.0297270.ref016","doi-asserted-by":"crossref","first-page":"666","DOI":"10.1080\/17461391.2020.1788651","article-title":"Demands of professional cycling races: influence of race category and result","volume":"21","author":"T Van Erp","year":"2021","journal-title":"European Journal of Sport Science"},{"key":"pone.0297270.ref017","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1016\/j.ins.2012.12.050","article-title":"Supporting athlete selection and strategic planning in track cycling omnium: a statistical and machine learning approach","volume":"233","author":"B Ofoghi","year":"2013","journal-title":"Information Sciences"},{"key":"pone.0297270.ref018","doi-asserted-by":"crossref","unstructured":"Ofoghi B, Zeleznikow J, MacMahon C, Dwyer D. A machine learning approach to predicting winning patterns in track cycling omnium. In: IFIP International Conference on Artificial Intelligence in Theory and Practice. Springer; 2010. p. 67\u201376.","DOI":"10.1007\/978-3-642-15286-3_7"},{"key":"pone.0297270.ref019","unstructured":"De Spiegeleer E. Predicting cycling results using machine learning. 2019;."},{"issue":"3","key":"pone.0297270.ref020","doi-asserted-by":"crossref","first-page":"e0229466","DOI":"10.1371\/journal.pone.0229466","article-title":"Estimating an individual\u2019s oxygen uptake during cycling exercise with a recurrent neural network trained from easy-to-obtain inputs: a pilot study","volume":"15","author":"A Zignoli","year":"2020","journal-title":"PLOS ONE"},{"key":"pone.0297270.ref021","unstructured":"Hilmkil A, Ivarsson O, Johansson M, Kuylenstierna D, van Erp T. Towards machine learning on data from professional cyclists. arXiv preprint arXiv:180800198. 2018;."},{"key":"pone.0297270.ref022","doi-asserted-by":"crossref","unstructured":"Kataoka Y, Gray P. Real-time power performance prediction in Tour de France. In: International Workshop on Machine Learning and Data Mining for Sports Analytics. Springer; 2018. p. 121\u2013130.","DOI":"10.1007\/978-3-030-17274-9_10"},{"key":"pone.0297270.ref023","doi-asserted-by":"crossref","DOI":"10.3389\/fspor.2021.714107","article-title":"A Learn-to-rank approach for predicting road cycling race outcomes","volume":"3","author":"L Kholkine","year":"2021","journal-title":"Frontiers in Sports and Active Living"},{"key":"pone.0297270.ref024","doi-asserted-by":"crossref","unstructured":"Leeuw AWd, Heijboer M, Hofmijster M, Zwaard Svd, Knobbe A. Time series regression in professional road cycling. In: International Conference on Discovery Science. Springer; 2020. p. 689\u2013703.","DOI":"10.1007\/978-3-030-61527-7_45"},{"key":"pone.0297270.ref025","first-page":"1","article-title":"Result-based talent identification in road cycling: discovering the next Eddy Merckx","author":"D Van Bulck","year":"2021","journal-title":"Annals of Operations Research"},{"issue":"1","key":"pone.0297270.ref026","doi-asserted-by":"crossref","first-page":"e0210191","DOI":"10.1371\/journal.pone.0210191","article-title":"A tactical comparison of the 4-2-3-1 and 3-5-2 formation in soccer: a theory-oriented, experimental approach based on positional data in an 11 vs. 11 game set-up","volume":"14","author":"D Memmert","year":"2019","journal-title":"PLOS ONE"},{"issue":"1","key":"pone.0297270.ref027","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-019-48623-1","article-title":"Clustering algorithm for formations in football games","volume":"9","author":"T Narizuka","year":"2019","journal-title":"Scientific Reports"},{"key":"pone.0297270.ref028","doi-asserted-by":"crossref","unstructured":"Schafer JB, Konstan J, Riedl J. Recommender systems in e-commerce. In: Proceedings of the 1st ACM conference on Electronic commerce; 1999. p. 158\u2013166.","DOI":"10.1145\/336992.337035"},{"issue":"Supplement 32","key":"pone.0297270.ref029","first-page":"175","article-title":"Knowledge-based recommender systems","volume":"69","author":"R Burke","year":"2000","journal-title":"Encyclopedia of Library and Information Sciences"},{"key":"pone.0297270.ref030","unstructured":"Basu C, Hirsh H, Cohen WW. Recommendation as Classification: Using Social and Content-Based Information in Recommendation. In: AAAI\/IAAI; 1998."},{"key":"pone.0297270.ref031","unstructured":"Corchado J, Lees B. Case-base reasoning recommendation system. In: IEEE Colloquium on Knowledge Discovery. London, UK; 1996."},{"key":"pone.0297270.ref032","doi-asserted-by":"crossref","unstructured":"Tak\u00e1cs G, Pil\u00e1szy I, N\u00e9meth B, Tikk D. Matrix factorization and neighbor based algorithms for the Netflix prize problem. In: Proceedings of the 2008 ACM Conference on Recommender Systems; 2008. p. 267\u2013274.","DOI":"10.1145\/1454008.1454049"},{"key":"pone.0297270.ref033","unstructured":"Aranda J, Givoni IE, Handcock J, Tarlow D. An Online Social Network-based Recommendation System; 2007."},{"key":"pone.0297270.ref034","unstructured":"Paterek A. Improving regularized singular value decomposition for collaborative filtering. In: Proceedings of KDD Cup and Workshop. vol. 2007; 2007. p. 5\u20138."},{"key":"pone.0297270.ref035","doi-asserted-by":"crossref","unstructured":"Pazzani MJ, Billsus D. Content-based recommendation systems. In: The Adaptive Web. Springer; 2007. p. 325\u2013341.","DOI":"10.1007\/978-3-540-72079-9_10"},{"key":"pone.0297270.ref036","doi-asserted-by":"crossref","unstructured":"Singh J. Collaborative filtering based hybrid music recommendation system. In: 2020 3rd International Conference on Intelligent Sustainable Systems (ICISS). IEEE; 2020. p. 186\u2013190.","DOI":"10.1109\/ICISS49785.2020.9315913"},{"key":"pone.0297270.ref037","doi-asserted-by":"crossref","unstructured":"Covington P, Adams J, Sargin E. Deep neural networks for youtube recommendations. In: Proceedings of the 10th ACM Conference on Recommender Systems; 2016. p. 191\u2013198.","DOI":"10.1145\/2959100.2959190"},{"key":"pone.0297270.ref038","doi-asserted-by":"crossref","unstructured":"Wu CSM, Garg D, Bhandary U. Movie recommendation system using collaborative filtering. In: 2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS). IEEE; 2018. p. 11\u201315.","DOI":"10.1109\/ICSESS.2018.8663822"},{"key":"pone.0297270.ref039","doi-asserted-by":"crossref","unstructured":"Fan W, Ma Y, Yin D, Wang J, Tang J, Li Q. Deep social collaborative filtering. In: Proceedings of the 13th ACM Conference on Recommender Systems; 2019. p. 305\u2013313.","DOI":"10.1145\/3298689.3347011"},{"key":"pone.0297270.ref040","doi-asserted-by":"crossref","unstructured":"Wang J, De Vries AP, Reinders MJ. Unifying user-based and item-based collaborative filtering approaches by similarity fusion. In: Proceedings of the 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval; 2006. p. 501\u2013508.","DOI":"10.1145\/1148170.1148257"},{"issue":"8","key":"pone.0297270.ref041","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1109\/MC.2009.263","article-title":"Matrix factorization techniques for recommender systems","volume":"42","author":"Y Koren","year":"2009","journal-title":"Computer"},{"key":"pone.0297270.ref042","unstructured":"Rashid A, Lam S, Karypis G, Riedl J. ClustKNN: a highly scalable hybrid model-& memory-based CF algorithm; 2006."},{"issue":"1","key":"pone.0297270.ref043","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1109\/TKDE.2004.1264822","article-title":"Probabilistic memory-based collaborative filtering","volume":"16","author":"K Yu","year":"2004","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"pone.0297270.ref044","doi-asserted-by":"crossref","unstructured":"Shardanand U, Maes P. Social information filtering: algorithms for automating \u201cword of mouth\u201d. In: Proceedings of the SIGCHI conference on Human Factors in Computing systems; 1995. p. 210\u2013217.","DOI":"10.1145\/223904.223931"},{"issue":"1","key":"pone.0297270.ref045","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1145\/963770.963776","article-title":"Item-based top-n recommendation algorithms","volume":"22","author":"M Deshpande","year":"2004","journal-title":"ACM Transactions on Information Systems (TOIS)"},{"key":"pone.0297270.ref046","unstructured":"Berndsen J, Lawlor A, Smyth B. Running with recommendation. In: HealthRecSys@RecSys; 2017. p. 18\u201321."},{"key":"pone.0297270.ref047","doi-asserted-by":"crossref","unstructured":"Smyth B. Recommender systems: a healthy obsession. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 33; 2019. p. 9790\u20139794.","DOI":"10.1609\/aaai.v33i01.33019790"},{"key":"pone.0297270.ref048","doi-asserted-by":"crossref","unstructured":"Berndsen J, Smyth B, Lawlor A. Pace my race: recommendations for marathon running. In: Proceedings of the 13th ACM Conference on Recommender Systems; 2019. p. 246\u2013250.","DOI":"10.1145\/3298689.3346991"},{"key":"pone.0297270.ref049","doi-asserted-by":"crossref","unstructured":"Matthews T, Ramchurn S, Chalkiadakis G. Competing with humans at fantasy football: team formation in large partially-observable domains. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 26; 2012.","DOI":"10.1609\/aaai.v26i1.8259"},{"issue":"2","key":"pone.0297270.ref050","first-page":"1","article-title":"Decision support system for a football team management by using machine learning techniques","volume":"10","author":"MAM Al-Asadi","year":"2018","journal-title":"Xinyang Teachers College"},{"issue":"6","key":"pone.0297270.ref051","doi-asserted-by":"crossref","first-page":"1546","DOI":"10.1109\/TMM.2012.2217121","article-title":"Recommender system for sport videos based on user audiovisual consumption","volume":"14","author":"F Sanchez","year":"2012","journal-title":"IEEE Transaction Multimedia"},{"key":"pone.0297270.ref052","doi-asserted-by":"crossref","first-page":"106699","DOI":"10.1016\/j.compeleceng.2020.106699","article-title":"A video information driven football recommendation system","volume":"85","author":"X Meng","year":"2020","journal-title":"Computers and Electrical Engineering"},{"key":"pone.0297270.ref053","doi-asserted-by":"crossref","unstructured":"Li L, Tong H, Cao N, Ehrlich K, Lin YR, Buchler N. Replacing the irreplaceable: Fast algorithms for team member recommendation. In: Proceedings of the 24th International Conference on World Wide Web; 2015. p. 636\u2013646.","DOI":"10.1145\/2736277.2741132"},{"key":"pone.0297270.ref054","unstructured":"Sagi M, Moskovitch R. Cyclists\u2019 workouts and race dataset download link. https:\/\/www.ise.bgu.ac.il\/clusters\/CyclistRaceData.zip."},{"key":"pone.0297270.ref055","first-page":"2825","article-title":"Scikit-learn: machine Learning in Python","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"pone.0297270.ref056","unstructured":"Dorogush AV, Ershov V, Gulin A. CatBoost: gradient boosting with categorical features support. arXiv preprint arXiv:181011363. 2018;."},{"key":"pone.0297270.ref057","unstructured":"Ho TK, et al. Proceedings of the 3rd International Conference on Document Analysis and Recognition. In: IEEE; 1995. p. 278\u2013282."},{"issue":"3","key":"pone.0297270.ref058","first-page":"358","article-title":"Classification and regression trees (CART)","volume":"40","author":"B Li","year":"1984","journal-title":"Biometrics"},{"key":"pone.0297270.ref059","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4899-3242-6","volume-title":"Generalized linear models","author":"P McCullagh","year":"1989"},{"key":"pone.0297270.ref060","unstructured":"Kira K, Rendell LA, et al. The feature selection problem: traditional methods and a new algorithm. In: AAAI. vol. 2; 1992. p. 129\u2013134."},{"key":"pone.0297270.ref061","unstructured":"CatBoost Feature Importance Description. Available from: https:\/\/catboost.ai\/en\/docs\/concepts\/fstr."},{"issue":"1","key":"pone.0297270.ref062","doi-asserted-by":"crossref","first-page":"2522","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"SM Lundberg","year":"2020","journal-title":"Nature Machine Intelligence"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0297270","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,4]],"date-time":"2024-03-04T18:22:32Z","timestamp":1709576552000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0297270"}},"subtitle":[],"editor":[{"given":"Jeremy B.","family":"Coquart","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2024,3,4]]},"references-count":62,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,3,4]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0297270","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,4]]}}}