[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126392-en":3,"doc-seo-126392-105":31,"detail-sidebar-cat-0-en-105":93},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126392,962085571259,"Theodora","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Predicting Soccer Matches with Complex Networks and Machine Learning - Research Highlights","Soccer match prediction is advanced by integrating complex networks with machine learning. The study builds passing networks from event-based match data and extracts complex-network metrics, then trains models to predict wins and losses across multiple leagues. Passing-network-based models achieve effectiveness comparable to traditional approaches that rely on general match statistics. Combining network metrics with conventional match features yields higher predictive accuracy than using either approach alone. Temporal granularity also matters, with networks split by match half outperforming a single network for the entire game.","Predicting soccer matches with complex networks and machine learning  \narXiv :2409 . 13098v 1 [ cs . SI] 19 Sep 2024  \nEduardo Alves Baratela, 1 Felipe Jordo Xavier, 1 Thomas Peron, 1, ∗ Paulino Ribeiro Villas-Boas,2 and Francisco Aparecido Rodrigues 1 1Instituto de Cieˆncias Matema´ticas˜ e de Computac¸a˜o, Universidade d˜e Sa˜o Paulo, Sa˜o Carlos 13566-590, Brazil  \n2 Embrapa Instrumentac¸ ao, Rua XV de Novembro, 1452, Sao Carlos, SP 13560-970, Brazil  \n(Dated: September 23, 2024)  \nSoccer attracts the attention of many researchers and professionals in the sports industry. Therefore, the incorporation of science into the sport is constantly growing, with increasing investments in performance analysis and sports prediction industries. This study aims to (i) highlight the use of complex networks as an alternative tool for predicting soccer match outcomes, and (ii) show how the combination of structural analysis of passing networks with match statistical data can provide deeper insights into the game patterns and strategies used by teams. In order to do so, complex network metrics and match statistics were used to build machine learning models that predict the wins and losses of soccer teams in different leagues. The results showed that models based on passing networks were as effective as “traditional” models, which use general match statistics. Another finding was that by combining both approaches, more accurate models were obtained than when they were used separately, demonstrating that the fusion of such approaches can offer a deeper understanding of game patterns, allowing the comprehension of tactics employed by teams relationships between players, their positions, and interactions during matches. It is worth mentioning that both network metrics and match statistics were important and impactful for the mixed model. Furthermore, the use of networks with a lower granularity of temporal evolution (such as creating a network for each half of the match) performed better than a single network for the entire game.  \nI. INTRODUCTION  \nThe prediction of soccer match results has been a topic of great interest in the scientific community and the sports industry. Various approaches have been proposed to tackle this problem, typically based on game statistics [1], player and team performance analyses [2], and other relevant metrics. However, many of these approaches are limited in their effectiveness and struggle to deal with the complexity and dynamics of player and team interactions.  \nOne promising approach that has gained traction is the application of network science to soccer. This involves the construction of passing networks, which provide a detailed representation of player interactions and game dynamics. Studies have demonstrated that analyzing these networks can yield valuable insights into team strategies and performance [3, 4] . For instance, Buld´u et al. [3] used network science to analyze Guardiola’s FC Barcelona, revealing distinct structural patterns in their passing network that differs from other teams, thus explaining their great performance through network metrics. Similarly, Gyarmati et al. [4] introduced the concept of“flow motifs” to characterize significant pass sequence patterns in soccer teams. Their analysis demonstrated that, while most teams employ a homogeneous playing style, unique strategies do exist.  \nIn addition to network science, machine learning has been extensively explored for predicting soccer outcomes. Techniques such as gradient-boosted trees have been employed to learn from relational data and predict match results with significant accuracy [1] . Machine learning models can leverage a variety of features, including historical match statistics and player performance metrics, to forecast future outcomes [5] .  \n∗ [thomas.peron@usp.br](thomas.peron@usp.br)  \nThis paper aims to bridge these two fields by evaluating whether the analysis of passing network structures can enhance the effectivenes","cbCaiczWuvKYXNQ8","https://ap.wps.com/l/cbCaiczWuvKYXNQ8","pdf",930735,9,1,12,"English","en",105,"# Introduction\n## Network science for soccer\n## Machine learning for match outcomes\n# Methodology\n## ETL / Data collecting\n## Passing network construction and feature extraction","[{\"question\":\"What is the main goal of the study on soccer match prediction?\",\"answer\":\"The study evaluates whether analyzing passing network structures can improve the effectiveness of machine learning models for predicting match outcomes.\"},{\"question\":\"How are predictions modeled in this research?\",\"answer\":\"Passing networks are constructed from event-based match data, complex-network metrics are extracted, and these metrics are used as inputs to machine learning models to predict wins and losses.\"},{\"question\":\"What effect does combining network metrics with traditional match statistics have?\",\"answer\":\"Fusion of the two approaches produces more accurate models than using network metrics or traditional features separately.\"}]","Predicting Soccer Matches with Complex Networks and Machine Learning - Research Highlights | PDF",1785904818,30,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"predicting-soccer-matches-with-complex-networks-and-machine-learning-research-highlights","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/predicting-soccer-matches-with-complex-networks-and-machine-learning-research-highlights/126392/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-21","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"What is the main goal of the study on soccer match prediction?","Question",{"text":77,"@type":78},"The study evaluates whether analyzing passing network structures can improve the effectiveness of machine learning models for predicting match outcomes.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"How are predictions modeled in this research?",{"text":82,"@type":78},"Passing networks are constructed from event-based match data, complex-network metrics are extracted, and these metrics are used as inputs to machine learning models to predict wins and losses.",{"name":84,"@type":75,"acceptedAnswer":85},"What effect does combining network metrics with traditional match statistics have?",{"text":86,"@type":78},"Fusion of the two approaches produces more accurate models than using network metrics or traditional features separately.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,112,117,122,124,128,131,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},5,"Comic",60,"comic",{"id":113,"doc_module":4,"doc_module_name":47,"category_name":114,"show_sort_weight":115,"slug":116},6,"Technology",50,"technology",{"id":118,"doc_module":4,"doc_module_name":47,"category_name":119,"show_sort_weight":120,"slug":121},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":30,"slug":123},"research-report",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":125,"show_sort_weight":126,"slug":127},"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":47,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":108,"slug":138},19,"General","general"]