{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T19:33:59Z","timestamp":1768073639024,"version":"3.49.0"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,5,28]],"date-time":"2024-05-28T00:00:00Z","timestamp":1716854400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,5,28]],"date-time":"2024-05-28T00:00:00Z","timestamp":1716854400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Discov Artif Intell"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The esports industry is one of the prominent business sectors in the digital era, particularly, Multiplayer Online Battle Arena (MOBA) games which gain much attention from gamers and streaming audiences. Among such games, Defense of the Ancient 2 or Dota 2 is the record holder for the highest prize esports tournament. Therefore, various companies and investors start their esports teams to compete in the Dota 2 tournaments, the Internationals. To success in the competition, player recruitment is a crucial process as it usually takes considerable effort to find a skillful player. Watching the game replay to evaluate the player\u2019s skill is one of the approaches. However, it can be too exhaustive, also some player\u2019s ranking, which represent the player\u2019s skill, are often not available. In this paper, we propose an effective machine learning pipeline to evaluate the player\u2019s skill. Our designed pipeline includes data collection, feature engineering, and machine learning modeling. We show the data collection process using open-source API. An effective method for feature engineering is proposed. Features, e.g., end-game, or tactical decision related statistics, are incorporated along with the resource in the game distribution, harassment tactic, or spatiotemporal features, in order to provide effective models. Subsequently, we apply major machine learning models based on a single game data, i.e., logistic regression and random forest, to the processed data. The most effective model can achieve up to 0.7091 precision, 0.5850 recall, 0.6411 F1-score, and 0.8123 ROC AUC score.<\/jats:p>","DOI":"10.1007\/s44163-024-00139-y","type":"journal-article","created":{"date-parts":[[2024,5,28]],"date-time":"2024-05-28T21:03:57Z","timestamp":1716930237000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Identifying player skill of dota 2 using machine learning pipeline"],"prefix":"10.1007","volume":"4","author":[{"given":"Methasit","family":"Pengmatchaya","sequence":"first","affiliation":[]},{"given":"Juggapong","family":"Natwichai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,5,28]]},"reference":[{"key":"139_CR1","doi-asserted-by":"publisher","unstructured":"Aung M, Bonometti V, Drachen A, et\u00a0al. Predicting skill learning in a large, longitudinal moba dataset. In: 2018 IEEE Conference on Computational Intelligence and Games (CIG), 2018;1\u20137, https:\/\/doi.org\/10.1109\/CIG.2018.8490431","DOI":"10.1109\/CIG.2018.8490431"},{"issue":"1","key":"139_CR2","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L. Random forests. Mach Learn. 2001;45(1):5\u201332. https:\/\/doi.org\/10.1023\/A:1010933404324.","journal-title":"Mach Learn"},{"key":"139_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4018\/IJGCMS.2016100101","volume":"8","author":"L Castaneda","year":"2016","unstructured":"Castaneda L, Sidhu M, Azose J, et al. Game play differences by expertise level in dota 2, a complex multiplayer video game. Int J Gaming Comput-Med Simul. 2016;8:1\u201324. https:\/\/doi.org\/10.4018\/IJGCMS.2016100101.","journal-title":"Int J Gaming Comput-Med Simul"},{"key":"139_CR4","doi-asserted-by":"publisher","unstructured":"Cavadenti O, Codocedo V, Boulicaut J, et\u00a0al. What did i do wrong in my moba game? mining patterns discriminating deviant behaviours. In: 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA), 2016;662\u2013671, https:\/\/doi.org\/10.1109\/DSAA.2016.75","DOI":"10.1109\/DSAA.2016.75"},{"key":"139_CR5","doi-asserted-by":"publisher","unstructured":"Chen T, Guestrin C. XGBoost: A scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, New York, NY, USA, KDD \u201916, 2016;785\u2013794, https:\/\/doi.org\/10.1145\/2939672.2939785,","DOI":"10.1145\/2939672.2939785"},{"key":"139_CR6","unstructured":"Chung H. parser. 2016; https:\/\/github.com\/odota\/parser"},{"issue":"3","key":"139_CR7","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/BF00994018","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes C, Vapnik V. Support-vector networks. Mach Learn. 1995;20(3):273\u201397.","journal-title":"Mach Learn"},{"key":"139_CR8","doi-asserted-by":"crossref","unstructured":"Demediuk S, York P, Drachen A, et al. Role identification for accurate analysis in dota 2. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment. 2019;15(1):130\u20138. https:\/\/ojs.aaai.org\/index.php\/AIIDE\/article\/view\/5235","DOI":"10.1609\/aiide.v15i1.5235"},{"key":"139_CR9","doi-asserted-by":"publisher","DOI":"10.1109\/GEM.2014.7048109","volume-title":"Skill-based differences in spatio-temporal team behaviour in defence of the ancients 2 (dota 2)","author":"A Drachen","year":"2014","unstructured":"Drachen A, Yancey M, Maguire J, et al. Skill-based differences in spatio-temporal team behaviour in defence of the ancients 2 (dota 2). Piscataway: IEEE; 2014."},{"key":"139_CR10","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1007\/978-3-319-24589-8_9","volume-title":"Entertainment computing - ICEC 2015","author":"C Eggert","year":"2015","unstructured":"Eggert C, Herrlich M, Smeddinck J, et al. Classification of player roles in the team-based multi-player game dota 2. In: Chorianopoulos K, Divitini M, Baalsrud Hauge J, et al., editors. Entertainment computing - ICEC 2015. Cham: Springer International Publishing; 2015. p. 112\u201325."},{"key":"139_CR11","unstructured":"Esports Earnings. Largest overall prize pools in esports. 2021a;https:\/\/www.esportsearnings.com\/tournaments"},{"key":"139_CR12","unstructured":"Esports Earnings. Paris saint-germain esports results for dota 2 (psg.lgd).2021b; https:\/\/www.esportsearnings.com\/teams\/623-paris-saint-germain-esports\/results\/2439-dota-2-psg-lgd"},{"key":"139_CR13","unstructured":"Esports Earnings. Top 100 highest overall earnings. 2021c;https:\/\/www.esportsearnings.com\/players"},{"key":"139_CR14","first-page":"335","volume":"8","author":"AE Fakazl\u0131","year":"2020","unstructured":"Fakazl\u0131 AE. The effect of covid-19 pandemic on digital games and esports. Int J Sport Cult Sci. 2020;8:335\u201344.","journal-title":"Int J Sport Cult Sci"},{"key":"139_CR15","unstructured":"Gao L, Judd J, Wong D, et\u00a0al. Classifying dota 2 hero characters based on play style and performance. Univ of Utah Course on ML 2013;"},{"key":"139_CR16","unstructured":"Hanke L, Chaimowicz L. A recommender system for hero line-ups in moba games. In: AIIDE 2017;"},{"key":"139_CR17","unstructured":"Hodge V, Devlin S, Sephton N, et\u00a0al. Win prediction in esports: Mixed-rank match prediction in multi-player online battle arena games. 2017;"},{"key":"139_CR18","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2019.2948469","author":"V Hodge","year":"2019","unstructured":"Hodge V, Devlin S, Sephton N, et al. Win prediction in multi-player esports: live professional match prediction. IEEE Trans Games. 2019. https:\/\/doi.org\/10.1109\/TG.2019.2948469.","journal-title":"IEEE Trans Games"},{"issue":"1","key":"139_CR19","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1080\/00401706.1970.10488634","volume":"12","author":"AE Hoerl","year":"1970","unstructured":"Hoerl AE, Kennard RW. Ridge regression: biased estimation for nonorthogonal problems. Technometrics. 1970;12(1):55\u201367. https:\/\/doi.org\/10.1080\/00401706.1970.10488634.","journal-title":"Technometrics"},{"key":"139_CR20","doi-asserted-by":"publisher","DOI":"10.1177\/14614448231187820","author":"KH Jensen","year":"2023","unstructured":"Jensen KH, Fynbo L, Hansen NN. The interplay between game design and social practice. New Media Soc. 2023. https:\/\/doi.org\/10.1177\/14614448231187820.","journal-title":"New Media Soc"},{"key":"139_CR21","unstructured":"Johansson F, Wikstr\u00f6m J. Result prediction by mining replays in dota 2 2015;"},{"key":"139_CR22","unstructured":"Johns T. All you need to know about dota 2 ranking system. 2024; https:\/\/dmarket.com\/blog\/dota2-ranks\/"},{"key":"139_CR23","doi-asserted-by":"publisher","unstructured":"Katona A, Spick R, Hodge VJ, et\u00a0al. Time to die: Death prediction in dota 2 using deep learning. In: 2019 IEEE Conference on Games (CoG), 2019;1\u20138, https:\/\/doi.org\/10.1109\/CIG.2019.8847997","DOI":"10.1109\/CIG.2019.8847997"},{"key":"139_CR24","doi-asserted-by":"publisher","unstructured":"K\u00f6nig R, Johansson U, Riveiro M, et\u00a0al. Modeling golf player skill using machine learning. In: International Cross-Domain Conference for Machine Learning and Knowledge Extraction : CD-MAKE 2017: Machine Learning and Knowledge Extraction, no. 10410 in Lecture Notes in Computer Science, pp 275\u2013294, 2017;https:\/\/doi.org\/10.1007\/978-3-319-66808-6_19","DOI":"10.1007\/978-3-319-66808-6_19"},{"key":"139_CR25","unstructured":"Newzoo. Global esports & live streaming market report. Newzoo: Tech. rep; 2021."},{"key":"139_CR26","doi-asserted-by":"publisher","DOI":"10.1145\/3343172","author":"L Pappalardo","year":"2019","unstructured":"Pappalardo L, Cintia P, Ferragina P, et al. Playerank: data-driven performance evaluation and player ranking in soccer via a machine learning approach. ACM Trans Intell Syst Technol. 2019. https:\/\/doi.org\/10.1145\/3343172.","journal-title":"ACM Trans Intell Syst Technol"},{"key":"139_CR27","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn: machine learning in python. J Mach Learn Res. 2011;12:2825\u201330.","journal-title":"J Mach Learn Res"},{"key":"139_CR28","doi-asserted-by":"publisher","unstructured":"Pobiedina N, Neidhardt J, Calatrava\u00a0Moreno MdC, et\u00a0al. Ranking factors of team success. In: Proceedings of the 22nd International Conference on World Wide Web. Association for Computing Machinery, New York, NY, USA, WWW \u201913 Companion, 2013;1185-1194, https:\/\/doi.org\/10.1145\/2487788.2488147,","DOI":"10.1145\/2487788.2488147"},{"key":"139_CR29","doi-asserted-by":"publisher","first-page":"907","DOI":"10.1007\/s11257-021-09300-z","volume":"31","author":"ACG Santos","year":"2021","unstructured":"Santos ACG, Oliveira W, Hamari J, et al. The relationship between user types and gamification designs. User Model User-Adapt Interaction. 2021;31:907\u201340.","journal-title":"User Model User-Adapt Interaction"},{"key":"139_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2020.101562","volume":"93","author":"V Sarlis","year":"2020","unstructured":"Sarlis V, Tjortjis C. Sports analytics - evaluation of basketball players and team performance. Inform Syst. 2020;93: 101562. https:\/\/doi.org\/10.1016\/j.is.2020.101562.","journal-title":"Inform Syst"},{"key":"139_CR31","unstructured":"Schordt M. Clarity 2. 2021; https:\/\/github.com\/skadistats\/clarity"},{"key":"139_CR32","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1007\/978-3-319-52920-2_3","volume-title":"Analysis of images, social networks and texts","author":"A Semenov","year":"2017","unstructured":"Semenov A, Romov P, Korolev S, et al. Performance of machine learning algorithms in predicting game outcome from drafts in dota 2. In: Ignatov DI, Khachay MY, Labunets VG, et al., editors. Analysis of images, social networks and texts. Cham: Springer International Publishing; 2017. p. 26\u201337."},{"key":"139_CR33","doi-asserted-by":"crossref","unstructured":"Wang N, Li L, Xiao L, et\u00a0al. Outcome prediction of dota2 using machine learning methods. In: ICMAI \u201918: Proceedings of 2018 International Conference on Mathematics and Artificial Intelligence, 2018;61\u201367","DOI":"10.1145\/3208788.3208800"},{"key":"139_CR34","unstructured":"Wells J. Dota 2 ranks: ranking system explained, mmr, and more. 2021; https:\/\/www.theloadout.com\/dota-2\/ranks"},{"key":"139_CR35","unstructured":"Yuen S, Thomson JD, Don O. Automatic player identification in dota 2. 2020;"},{"key":"139_CR36","unstructured":"Zoid. Dota 2 match history webapi. 2012; https:\/\/dev.dota2.com\/forum\/dota-2\/spectating\/replays\/webapi\/48733-dota-2-match-history-webapi"}],"container-title":["Discover Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44163-024-00139-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44163-024-00139-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44163-024-00139-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,28]],"date-time":"2024-05-28T21:09:06Z","timestamp":1716930546000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44163-024-00139-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,28]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["139"],"URL":"https:\/\/doi.org\/10.1007\/s44163-024-00139-y","relation":{},"ISSN":["2731-0809"],"issn-type":[{"value":"2731-0809","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,28]]},"assertion":[{"value":"20 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 May 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 May 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We wish to confirm that there are no known competing interests associated with this publication and there has been no significant financial support for this work that could have influenced its outcome.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"41"}}