[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127131-en":3,"doc-seo-127131-105":30,"detail-sidebar-cat-0-en-105":91},{"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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},127131,687207022233,"Riley","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","A Hybrid Machine Learning Framework for Soccer Match Outcome Prediction - Incorporating Bivariate Poisson Distribution","A hybrid framework combines statistical modeling and machine learning to predict soccer match outcomes and support decision-making for academic research and long-term betting. Using a comprehensive dataset from the top European leagues (2014–2022), the study applies Bivariate Poisson distribution and compares it with Naive Bayes, Neural Networks, Support Vector Machines, Random Forests, and Gradient Boosting. Feature engineering merges historical match statistics, FIFA ratings, and betting odds. Results show Random Forests achieve the highest accuracy (56.25%), while draw prediction remains the key challenge, motivating future work on improved draw modeling and profitability analysis.","A Hybrid Machine Learning Framework for  \nSoccer Match Outcome Prediction:  \nIncorporating Bivariate Poisson Distribution  \nZhong An Chen  \nBASIS International School Guangzhou, 8 Jiantashan Rd, Huangpu District, Guangzhou, Guangdong, China, 510653  \nAbstract. The 2022 FIFA World Cup final attracted 1.5 billion viewers, while billions of dollars are wagered on soccer matches every year. The increasing demand for accurate predictions, both for academic research and betting purposes, has driven the development of advanced forecasting models. This study explores the application of mathematical and machine learning models to predict results of soccer matches, with the dual aim of academic advancement and profitable betting. The author utilizes a comprehensive dataset from top European leagues (2014-2022) and employ models including Bivariate Poisson Distribution, Naive Bayes, Neural Networks, Support Vector Machines, Random Forests, and Gradient Boosting. The paper’s feature engineering combines historical match statistics, FIFA ratings, and betting odds. While Random Forests achieved the highest accuracy (56.25%), predicting draws remains challenging. The study highlights the potential for improved prediction systems and suggests future research in advanced draw prediction techniques and profitability analysis, the paper provides research directions for researchers in related fields.  \n1 Introduction  \nSoccer, football in British, is the most fascinating sport in the world. In the 2022 FIFA Qatar World Cup, 88966 spectators crowded into Lusail Stadium, and about 1.5 billion people watched this game. When it comes to soccer leagues, the English Premier League is the most popular soccer league in the world, with an online audience around 4.7 billion people. The reason for the author to predict soccer game results is not only to progress in academics but also to strive for a large amount of profit in soccer betting. During the whole period of the World Cup, a total of $35 billion dollars is used by people for soccer betting.  \nMathematical models and machine learning models are widely used in different areas, such as finance credit prediction [1], basketball result prediction [2], and American football result prediction [3] . All the studies above demonstrated that mathematical models and machine learning are suitable for sports analytics and prediction, specifically in classifying win, draw, and lose.  \nCorresponding author: [zhongan.chen17296-bigz@basischina.com](zhongan.chen17296-bigz@basischina.com)  \n© The Authors, published by EDP Sciences. This is an open access article distributed under the terms of the Creative Commons Attribution License 4.0 ([https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/)).  \nIn terms of soccer, scholars have already pursued predicting the result of this sport. Initially, Stefani [4] used a linear regression to calculate the rating of different teams, and dida simple comparison of teams’ ratings to decide the winning team. Yip [5] used a Bivariate Poisson model to predict the expected goals and corners for each game to find the final result. Mwembe [6] applied a bivariate Poisson model to predict the soccer game result in Zimbabwe premier soccer league. Besides mathematical models, Machine Learning (ML) was also employed in developing a prediction system. For example, Baboota [7] used various machine learning models to build a predictive system with a better performance compared to mathematical models. According to Baboota [7], their models have similar accuracy and all of them have a higher accuracy than the predictive system made by bookmakers, Bet365 . Although they technically gained a positive expected value in soccer betting, they only focused on English Premier League matches, resulting in a limited amount of both training and testing data. What’s more, they were still struggling to correctly predict draws.  \nThe objective of this study is to develop a r","cbCaikDAnebiUacI","https://ap.wps.com/l/cbCaikDAnebiUacI","pdf",937855,1,15,"English","en",105,"# Introduction\n# Feature Engineering\n## Data Acquisition and Cleaning\n## Feature Selection","[{\"question\":\"What data and leagues are used to train and test the prediction models?\",\"answer\":\"The study uses a public Kaggle dataset covering the top five European leagues from 2014 to 2022: English Premier League, La Liga, Bundesliga, Serie A, and Ligue 1.\"},{\"question\":\"Which models are compared in the hybrid prediction framework?\",\"answer\":\"The framework includes Bivariate Poisson distribution and compares machine learning models such as Naive Bayes, Neural Networks, Support Vector Machines, Random Forests, and Gradient Boosting.\"},{\"question\":\"How are the input features engineered for better prediction?\",\"answer\":\"Features combine historical match statistics aggregated over the previous k games, FIFA ratings, and betting odds to form indicators for current match prediction.\"}]","A Hybrid Machine Learning Framework for Soccer Match Outcome Prediction - Incorporating Bivariate Poisson Distribution | PDF",1785937055,38,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"a-hybrid-machine-learning-framework-for-soccer-match-outcome-prediction-incorporating-bivariate-poisson-distribution","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/a-hybrid-machine-learning-framework-for-soccer-match-outcome-prediction-incorporating-bivariate-poisson-distribution/127131/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What data and leagues are used to train and test the prediction models?","Question",{"text":75,"@type":76},"The study uses a public Kaggle dataset covering the top five European leagues from 2014 to 2022: English Premier League, La Liga, Bundesliga, Serie A, and Ligue 1.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which models are compared in the hybrid prediction framework?",{"text":80,"@type":76},"The framework includes Bivariate Poisson distribution and compares machine learning models such as Naive Bayes, Neural Networks, Support Vector Machines, Random Forests, and Gradient Boosting.",{"name":82,"@type":73,"acceptedAnswer":83},"How are the input features engineered for better prediction?",{"text":84,"@type":76},"Features combine historical match statistics aggregated over the previous k games, FIFA ratings, and betting odds to form indicators for current match prediction.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]