[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126693-en":3,"doc-seo-126693-105":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},126693,962084925636,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Regression based machine learning on the FIFA Ultimate Team transfer market - Master of Science Thesis","This Master of Science thesis investigates how machine learning regression models can be used to predict item prices for new players entering EA Sports’ FIFA Ultimate Team transfer market. The study motivates improved pricing accuracy to enhance player experience and reduce real-money currency exploitation. It explains FUT mechanics, reviews related research, describes data gathering and filtering, and details feature engineering including performance, chemistry, and position-specific aspects. Multiple regression and ensemble models are evaluated with performance metrics, followed by an analysis of key issues when prediction quality is insufficient and concluding findings.","Regression based machine learning on the FIFA Ultimate Team transfer market  \nMaster of Science Thesis  \nUniversity of Turku  \nDepartment of computing  \nData analytics  \n2023  \nJaakko Kittilä  \nThe originality of this thesis has been checked in accordance with the University of Turku quality assurance system using the Turnitin OriginalityCheck service.  \nUNIVERSITY OF TURKU Department of computing  \nJaakko Kittilä : Regression based machine learning on the FIFA Ultimate Team transfer market  \nMaster of Science Thesis, 36 s.  \nData analytics August 2023  \nUltimate Team is a highly popular game mode in the FIFA video game series developed by EA Sports. In Ultimate Team, players can buy and sell items based on real players on the transfer market with an in game currency. To combat buying and selling the currency with real money, the items have a price range set on the transfer market so that each item can only be sold for a reasonable price based on the item’s abilities.  \nThis thesis demonstrates how machine learning regression models could be used to predict the prices of new items entering the game, so that the price ranges could beset more accurately to improve player experience. As the predictions weren’t good enough to improve the current situation, the thesis goes through what are biggest issues in making the predictions.  \nAsiasanat: regression, machine learning  \nTable of contents  \n1 Introduction, background and inspiration 1  \n1.1 The purpose of this thesis ........................ 1  \n1.2 Ultimate Team explained ......................... 2  \n1.3 Inspiration ................................. 3  \n2 Similar research 5  \n2.1 Using FUT data for other purposes ................... 5  \n2.2 Other FUT related studies ........................ 6  \n3 Gathering data, data format and first data filtering 9  \n3.1 Gathering data .............................. 9  \n3.2 Data files and format ........................... 10  \n3.3 Data filtering ............................... 10  \n3.4 Missing values and fixes to data ..................... 12  \n3.5 Live items ................................. 13  \n4 Approach to making predictions and features used 14  \n4.1 Techniques used .............................. 14  \n4.2 Performance metrics ........................... 14  \n4.2.1 Regression performance metrics ................. 14  \n4.2.2 Other performance metrics .................... 16  \n4.3 Setup for making predictions ....................... 16  \n4.4 Feature scaling .............................. 17  \n4.5 Prediction minimum and maximum values ............... 20  \n5 Features tested and used 21  \n5.1 Performance based features ....................... 21  \n5.2 Chemistry based features ......................... 22  \n5.3 Others ................................... 24  \n5.4 Goalkeepers ................................ 24  \n5.5 Features used ............................... 25  \n6 Models tested and model performances 26  \n6.1 Models chosen ............................... 26  \n6.1.1 Neighbors regression ....................... 26  \n6.1.2 Linear regression ......................... 27  \n6.1.3 Decision tree: ........................... 27  \n6.1.4 Ensemble methods ........................ 28  \n6.1.5 Neural networks .......................... 28  \n6.2 Model performances ........................... 29  \n6.2.1 Regression model performances ................. 29  \n6.2.2 Other metric performances .................... 29  \n7 Prediction results 31  \n7.1 Results overview ............................. 31  \n7.2 Third quartile ............................... 32  \n7.3 Missing features .............................. 34  \n8 Conclusion 35  \n8.1 Summary ................................. 35  \nReferences 37  \nFigures  \n3.1 Boxplots of average prices of all gold players (left) and all silver players (right) ................................... 12  \n4.1 Flowchart of how predicting the values of all new items was done... 19  \nTables  \n6.1 Table of models chosen for testing and their","cbCaiiJcYrWJSgBu","https://ap.wps.com/l/cbCaiiJcYrWJSgBu","pdf",246277,1,46,"English","en",105,"# Introduction, background and inspiration\n## The purpose of this thesis\n## Ultimate Team explained\n## Inspiration\n# Similar research\n## Using FUT data for other purposes\n## Other FUT related studies\n# Gathering data, data format and first data filtering\n## Gathering data\n## Data files and format\n## Data filtering\n## Missing values and fixes to data\n## Live items\n# Approach to making predictions and features used\n## Techniques used\n## Performance metrics\n## Setup for making predictions\n## Feature scaling\n## Prediction minimum and maximum values\n# Features tested and used\n## Performance based features\n## Chemistry based features\n## Others\n## Goalkeepers\n## Features used\n# Models tested and model performances\n## Models chosen\n## Model performances\n## Prediction results\n# Conclusion","[{\"question\":\"What is the main goal of the thesis in the FIFA Ultimate Team context?\",\"answer\":\"The thesis aims to predict prices of new players entering FIFA Ultimate Team using regression-based machine learning, to improve player experience and reduce chances of cheating.\"},{\"question\":\"How does the thesis handle data preparation for transfer market predictions?\",\"answer\":\"It covers gathering and storing FUT data, filtering relevant parts, addressing missing values, and defining how live items are treated before modeling.\"},{\"question\":\"Which modeling approaches and evaluation metrics are used?\",\"answer\":\"The work tests multiple regression models such as k-nearest neighbors, linear regression, decision trees, ensemble methods, and neural networks, evaluating them with regression-specific metrics and additional performance metrics.\"}]","Regression based machine learning on the FIFA Ultimate Team transfer market - Master of Science Thesis | PDF",1785934259,116,{"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},"regression-based-machine-learning-on-the-fifa-ultimate-team-transfer-market-master-of-science-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/regression-based-machine-learning-on-the-fifa-ultimate-team-transfer-market-master-of-science-thesis/126693/",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 is the main goal of the thesis in the FIFA Ultimate Team context?","Question",{"text":75,"@type":76},"The thesis aims to predict prices of new players entering FIFA Ultimate Team using regression-based machine learning, to improve player experience and reduce chances of cheating.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the thesis handle data preparation for transfer market predictions?",{"text":80,"@type":76},"It covers gathering and storing FUT data, filtering relevant parts, addressing missing values, and defining how live items are treated before modeling.",{"name":82,"@type":73,"acceptedAnswer":83},"Which modeling approaches and evaluation metrics are used?",{"text":84,"@type":76},"The work tests multiple regression models such as k-nearest neighbors, linear regression, decision trees, ensemble methods, and neural networks, evaluating them with regression-specific metrics and additional performance metrics.","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"]