{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T19:11:03Z","timestamp":1771701063353,"version":"3.50.1"},"reference-count":35,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2023,3,24]],"date-time":"2023-03-24T00:00:00Z","timestamp":1679616000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"University North and Ministry of Science and Education, Republic of Croatia","award":["UNIN-TEH-22-1-12"],"award-info":[{"award-number":["UNIN-TEH-22-1-12"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>We propose a new, data-driven model for the prediction of the outcomes of NBA and possibly other basketball league games by using machine learning methods. The paper starts with a strict mathematical formulation of the basketball statistical quantities and the performance indicators derived from them. The backbone of our model is the extended team efficiency index, which consists of two asymmetric parts: (i) the team efficiency index, generally based on some individual efficiency index\u2014in our case, the NBA player efficiency index, and (ii) the comparing part, in which the observed team is rewarded for every selected feature in which it outperforms its rival. Based on the average of the past extended indices, the predicted extended indices are calculated symmetrically for both teams competing in the observed future game. The relative value of those indices defines the win function, which predicts the game outcome. The prediction model includes the concept of the optimal time window (OTW) for the training data. The training datasets were extracted from maximally four and the testing datasets from maximally two of the five consecutive observed NBA seasons (2013\/2014\u20132017\/2018). The model uses basic, derived, advanced, and league-wise basketball game elements as its features, whose preparation and extraction were briefly discussed. The proposed model was tested for several choices of the training and testing sets\u2019 seasons, without and with OTWs. The average obtained prediction accuracy is around 66%, and the maximal obtained accuracy is around 78%. This is satisfactory and in the range of better results in the works of other authors.<\/jats:p>","DOI":"10.3390\/sym15040798","type":"journal-article","created":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T04:05:40Z","timestamp":1679889940000},"page":"798","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["A Data-Driven Machine Learning Algorithm for Predicting the Outcomes of NBA Games"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8358-3218","authenticated-orcid":false,"given":"Tomislav","family":"Horvat","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, University North, 104. Brigade 3, 42000 Varazdin, Croatia, EU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6998-5907","authenticated-orcid":false,"given":"Josip","family":"Job","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering, Computer Science and Information Technology, J. J. Strossmayer University of Osijek, Kneza Trpimira 2B, 31000 Osijek, Croatia, EU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3303-2271","authenticated-orcid":false,"given":"Robert","family":"Logozar","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, University North, 104. Brigade 3, 42000 Varazdin, Croatia, EU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1027-7006","authenticated-orcid":false,"given":"\u010caslav","family":"Livada","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering, Computer Science and Information Technology, J. J. Strossmayer University of Osijek, Kneza Trpimira 2B, 31000 Osijek, Croatia, EU"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,3,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Alpaydin, E. (2020). Introduction to Machine Learning, MIT Press.","DOI":"10.7551\/mitpress\/13811.001.0001"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Prasetio, D., and Harlili, D. (2016, January 16\u201319). Predicting football match results with logistic regression. Proceedings of the 2016 International Conference On Advanced Informatics: Concepts, Theory And Application (ICAICTA), Penang, Malaysia.","DOI":"10.1109\/ICAICTA.2016.7803111"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1016\/j.ijforecast.2011.05.002","article-title":"A comparative analysis of data mining methods in predicting NCAA bowl outcomes","volume":"28","author":"Delen","year":"2012","journal-title":"Int. J. Forecast."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1515\/ijcss-2016-0007","article-title":"Predicting Win-Loss outcomes in MLB regular season games \u2013 A comparative study using data mining methods","volume":"15","author":"Valero","year":"2016","journal-title":"Int. J. Comput. Sci. Sport"},{"key":"ref_5","unstructured":"Elfrink, T. (2018). Predicting the Outcomes of MLB Games with a Machine Learning Approach, Vrije Universiteit Amsterdam."},{"key":"ref_6","doi-asserted-by":"crossref","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 Min. Knowl. Discov."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Loeffelholz, B., Bednar, E., and Bauer, K.W. (2009). Predicting NBA games using neural networks. J. Quant. Anal. Sport., 5.","DOI":"10.2202\/1559-0410.1156"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Miljkovi\u0107, D., Gaji\u0107, L., Kova\u010devi\u0107, A., and Konjovi\u0107, Z. (2010, January 10\u201311). The use of data mining for basketball matches outcomes prediction. Proceedings of the IEEE 8th International Symposium on Intelligent Systems and Informatics, Subotica, Serbia.","DOI":"10.1109\/SISY.2010.5647440"},{"key":"ref_9","unstructured":"Zdravevski, E., and Kulakov, A. (2009). Proceedings of the International Conference on ICT Innovations, Springer."},{"key":"ref_10","unstructured":"(2022, March 03). Weka 3: Machine Learning Software in Java. Available online: https:\/\/www.cs.waikato.ac.nz\/ml\/weka\/."},{"key":"ref_11","unstructured":"Kravanja, A. (2013). Napovedanje Zmagovalcev Ko\u0161arka\u0161kih Tekem. [Doctoral dissertation, Univerza v Ljubljani]."},{"key":"ref_12","unstructured":"Torres, R.A. (2013). Prediction of NBA Games Based on Machine Learning Methods, University of Wisconsin."},{"key":"ref_13","unstructured":"Lin, J., Short, L., and Sundaresan, V. (2014). Predicting national basketball association winners. CS 229 FINAL PROJECT, 1\u20135."},{"key":"ref_14","unstructured":"Tran, T. (2016). Predicting NBA Games with Matrix Factorization. [Ph.D. Thesis, Massachusetts Institute of Technology]."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Cheng, G., Zhang, Z., Kyebambe, M.N., and Kimbugwe, N. (2016). Predicting the outcome of NBA playoffs based on the maximum entropy principle. Entropy, 18.","DOI":"10.20944\/preprints201609.0103.v1"},{"key":"ref_16","unstructured":"Avalon, G., Balci, B., and Guzman, J. (2016). Various Machine Learning Approaches to Predicting NBA Score Margins, 2016. Final Project."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"4159","DOI":"10.1007\/s00521-016-2321-9","article-title":"Analyzing basketball games by a support vector machines with decision tree model","volume":"28","author":"Pai","year":"2017","journal-title":"Neural Comput. Appl."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1515\/jaiscr-2018-0011","article-title":"One-match-ahead forecasting in two-team sports with stacked Bayesian regressions","volume":"8","author":"Lam","year":"2018","journal-title":"J. Artif. Intell. Soft Comput. Res."},{"key":"ref_19","unstructured":"Ganguly, S., and Frank, N. (2018, January 23\u201324). The problem with win probability. Proceedings of the 2018 MIT Sloan Sports Analytics Conference, Boston, MA, USA."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Ivankovi\u0107, Z., Rackovi\u0107, M., Markoski, B., Radosav, D., and Ivkovi\u0107, M. (2010, January 18\u201320). Analysis of basketball games using neural networks. Proceedings of the 2010 11th International Symposium on Computational Intelligence and Informatics (CINTI), IEEE, Budapest, Hungary.","DOI":"10.1109\/CINTI.2010.5672237"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Trawi\u0144ski, K. (2010, January 10\u201312). A fuzzy classification system for prediction of the results of the basketball games. Proceedings of the International Conference on Fuzzy Systems, IEEE, Yantai, China.","DOI":"10.1109\/FUZZY.2010.5584399"},{"key":"ref_22","unstructured":"Zimmermann, A., Moorthy, S., and Shi, Z. (2013). Predicting college basketball match outcomes using machine learning techniques: Some results and lessons learned. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Horvat, T., Job, J., and Medved, V. (2018, January 20\u201321). Prediction of Euroleague games based on supervised classification algorithm k-nearest neighbours. Proceedings of the 6th International Congress on Support Sciences Research and Technology Support, Setubal, Portugal.","DOI":"10.5220\/0006893502030207"},{"key":"ref_24","unstructured":"Manley, M. (1989). Martin Manley\u2019s Basketball Heaven, Doubleday Books."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/0893-6080(88)90021-4","article-title":"Nonlinear neural networks: Principles, mechanisms, and architectures","volume":"1","author":"Grossberg","year":"1988","journal-title":"Neural Netw."},{"key":"ref_26","first-page":"1205","article-title":"Efficient Feature Selection via Analysis of Relevance and Redundancy","volume":"5","author":"Yu","year":"2004","journal-title":"J. Mach. Learn. Res."},{"key":"ref_27","unstructured":"Han, J., and Kamber, M. (2006). Data Mining: Concepts and Techniques, The Morgan Kaufmann Series in Data Management Systems; Elsevier: Amsterdam, The Netherlands; Morgan Kaufmann: Burlington, MA, USA; Boston: San Francisco, CA, USA. [2nd ed.]."},{"key":"ref_28","unstructured":"(2022, March 03). Basketball Stats and History Statistics, Scores, and History for the NBA, ABA, WNBA, and Top European Competition. Available online: https:\/\/www.basketball-reference.com."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Horvat, T., Havas, L., and Medved, V. (2015, January 15\u201317). Web Application for Support in Basketball Game Analysis. Proceedings of the icSPORTS, Lisbon, Portugal.","DOI":"10.5220\/0005591102250231"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Horvat, T., Havas, L., Srpak, D., and Medved, V. (2019, January 20\u201321). Data-driven Basketball Web Application for Support in Making Decisions. Proceedings of the icSPORTS, Vienna, Austria.","DOI":"10.5220\/0008388102390244"},{"key":"ref_31","first-page":"197","article-title":"Importance of the training dataset length in basketball game outcome prediction by using na\u00efve classification machine learning methods","volume":"86","author":"Horvat","year":"2019","journal-title":"Elektrotehni\u0161ki Vestn."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Horvat, T., Hava\u0161, L., and Srpak, D. (2020). The impact of selecting a validation method in machine learning on predicting basketball game outcomes. Symmetry, 12.","DOI":"10.3390\/sym12030431"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1109\/5326.897072","article-title":"Neural networks for classification: A survey","volume":"30","author":"Zhang","year":"2000","journal-title":"IEEE Trans. Syst. Man Cybern. Part C"},{"key":"ref_34","unstructured":"(2022, March 03). Dean Oliver. Available online: https:\/\/en.wikipedia.org\/wiki\/Dean_Oliver_(statistician)."},{"key":"ref_35","unstructured":"Horvat, T. (2020). An Adaptive Method for Predicting Sport Outcomes Based on the Efficiency Index and Optimal Time Window. [Ph.D. Thesis, Faculty of Electrical Engineering, Computer Science and Information Technology, University of Osijek]."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/15\/4\/798\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:02:38Z","timestamp":1760122958000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/15\/4\/798"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,24]]},"references-count":35,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,4]]}},"alternative-id":["sym15040798"],"URL":"https:\/\/doi.org\/10.3390\/sym15040798","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,24]]}}}