[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125815-en":3,"doc-seo-125815-105":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},125815,4398048949847,"Eliana","https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267",8,"Research & Report","Determining Best Sports Ranking Method with Machine Learning Techniques - Thesis","The thesis examines how abundant sports data can enhance analytics and machine learning for ranking teams, addressing limitations of standard league ranking approaches. It builds improved Bradley-Terry model ranking systems for the NFL, NBA, NHL, and MLB and uses the resulting ranks to compute new win probabilities for individual games. The outcomes feed into neural networks to improve matchup prediction, with best models using ridge-penalized logistic regression and home-court advantage to increase predictive accuracy by up to 17% versus a home-win baseline.","UCLA  \nUCLA Electronic Theses and Dissertations  \nTitle  \nDetermining Best Sports Ranking Method with Machine Learning Techniques  \nPermalink  \n[https://escholarship.org/uc/item/4bj148mb](https://escholarship.org/uc/item/4bj148mb)  \nAuthor  \nCastillo, Robert  \nPublication Date  \n2024  \nSupplemental Material  \n[https://escholarship.org/uc/item/4bj148mb\\#supplemental](https://escholarship.org/uc/item/4bj148mb#supplemental)  \n[Peer reviewed|Thesis/dissertation](Peer reviewed|Thesis/dissertation)  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nUNIVERSITY OF CALIFORNIA Los Angeles  \nDetermining Best Sports Ranking Method with Machine Learning Techniques  \nA thesis submitted in partial satisfaction of the requirements for the degree Master of Applied Statistics & Data Science  \nby  \nRobert Castillo  \n2024  \n© Copyright by Robert Castillo  \n2024  \nABSTRACT OF THE THESIS  \nDeterming Best Sports Ranking Methods with  \nMachine Learning Techniques  \nby  \nRobert Castillo  \nMaster of Applied Statistics & Data Science  \nUniversity of California, Los Angeles, 2024  \nProfessor Yingnian Wu, Chair  \nThe increase in available sports data has allowed for an increased role in data analyticsand machine learning in sports. Most notably, statistical methods have been used to try and predict the outcomes of games, which has given rise to sports betting. While this technological advancement can provide teams and viewers with an improved understanding of ways certain teams perform better than others, the leagues stick with standard, and often flawed, ways of ranking teams. In the following project, various methods are used to create enhanced Bradley Terry model ranking systems for each of the four major sports leagues in North America: the NFL, NBA, NHL, and MLB. These rankings will be used to calculate new win probabilities for each game. These results, along with other variables, will be used as inputs for neural networks that aim to improve the predictive capabilities for game matchups. The best models created using each sport’s dataset involved using the logistic regression ranking method that utilized the Ridge Regression penalty and home court advantage, improving predictive accuracy by as much as 17% compared to simply predicting that the home team will win.  \nThe thesis of Robert Castillo is approved.  \nGeorge Michailidis Michael Tsiang Yingnian Wu, Committee Chair  \nUniversity of California, Los Angeles 2024  \nTo my family    \nThank you for your unconditional support  \niv  \nTABLE OF CONTENTS  \n1 Introduction ..................................... 1  \n2 Methodology ..................................... 4  \n2.1 Overview ...................................... 4  \n2.2 Data Collection and Feature Engineering .................... 6  \n2.2.1 Kaggle ................................... 6  \n2.2.2 Sports-Statistics .............................. 6  \n2.2.3 Feature Engineering ........................... 7  \n2.3 Bradley Terry Model ............................... 9  \n2.3.1 Iterative Approach ............................ 10  \n2.3.2 Logistic Regression ............................ 11  \n2.4 Neural Networks ................................. 15  \n2.4.1 Multilayer Perceptron (MLP) ...................... 16  \n3 Results ......................................... 21  \n3.1 NFL ........................................ 23  \n3.2 NBA ........................................ 28  \n3.3 NHL ........................................ 34  \n3.4 MLB ........................................ 38  \n3.5 Sport Comparison ................................. 43  \n4 Conclusion ....................................... 49  \n4.1 Overview ...................................... 49  \n4.2 Limitations .................................... 50  \n4.3 Future Work .................................... 51  \nReferences ......................................... 53  \nLIST OF FIGURES  \n3.1 NFL Loss Comparison .............................. 23  \n3.2 NFL T","cbCaiaYPOYKQhncn","https://ap.wps.com/l/cbCaiaYPOYKQhncn","pdf",523797,1,63,"English","en",105,"# Introduction\n# Methodology\n## Overview\n## Data Collection and Feature Engineering\n## Bradley Terry Model\n## Neural Networks\n# Results\n## NFL\n## NBA\n## NHL\n## MLB\n## Sport Comparison\n# Conclusion\n## Limitations\n## Future Work","[{\"question\":\"What problem does the thesis address in sports team ranking?\",\"answer\":\"It addresses how leagues rely on standard, often flawed ranking methods despite the growing availability of sports data that could support better analytics and machine learning.\"},{\"question\":\"How are the Bradley-Terry ranking systems used in the project?\",\"answer\":\"Enhanced Bradley-Terry models are created for the NFL, NBA, NHL, and MLB, and the rankings are used to calculate win probabilities for each game.\"},{\"question\":\"Which modeling approach produced the best predictive accuracy and why?\",\"answer\":\"The best models used logistic regression with a Ridge Regression penalty and included home-court advantage, improving predictive accuracy by as much as 17% compared with predicting the home team would win.\"}]","Determining Best Sports Ranking Method with Machine Learning Techniques - Thesis | PDF",1785901361,159,{"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},"determining-best-sports-ranking-method-with-machine-learning-techniques-thesis","",{"@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/determining-best-sports-ranking-method-with-machine-learning-techniques-thesis/125815/",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 problem does the thesis address in sports team ranking?","Question",{"text":75,"@type":76},"It addresses how leagues rely on standard, often flawed ranking methods despite the growing availability of sports data that could support better analytics and machine learning.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are the Bradley-Terry ranking systems used in the project?",{"text":80,"@type":76},"Enhanced Bradley-Terry models are created for the NFL, NBA, NHL, and MLB, and the rankings are used to calculate win probabilities for each game.",{"name":82,"@type":73,"acceptedAnswer":83},"Which modeling approach produced the best predictive accuracy and why?",{"text":84,"@type":76},"The best models used logistic regression with a Ridge Regression penalty and included home-court advantage, improving predictive accuracy by as much as 17% compared with predicting the home team would win.","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"]