[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124262-en":3,"doc-seo-124262-105":30,"detail-sidebar-cat-0-en-105":90},{"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},124262,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","High School to NCAA - Predicting Freshman Impact in College Basketball with Machine Learning","A predictive research project for college basketball focuses on estimating a high school player’s freshman impact at high-major programs in the SEC-level range. The work addresses changing athlete-management conditions following April 2025 rulings and links roster decisions to data-driven evaluation. Using Synergy Sports data and multi-year AAU and NCAA statistics, the study constructs a stacked WARP-based ensemble that produces season WARP estimates and minute-play probability outputs. Results report an average Mean Absolute Error of 1.83 WARP for 2024–2025 freshmen.","University of Tennessee, Knoxville  \nTRACE: Tennessee Research and Creative Exchange  \n\n| EURēCA: Exhibition of Undergraduate Research and Creative Achievement | Supervised Undergraduate Student Research and Creative Work |\n| --- | --- |\n| April 2025\u003Cbr>High School to NCAA: Predicting Freshman Impact in College Basketball with Machine Learning\u003Cbr>Timothy Held\u003Cbr>University of Tennessee, Knoxville, [theld1@vols.utk.edu](theld1@vols.utk.edu)\u003Cbr>Follow this and additional works at: [https://trace.tennessee.edu/eureca](https://trace.tennessee.edu/eureca)\u003Cbr> Part of the Business Analytics Commons, Business Intelligence Commons, Data Science Commons, and the Sports Management Commons |  |\n\nRecommended Citation  \nHeld, Timothy, \"High School to NCAA: Predicting Freshman Impact in College Basketball with Machine Learning\" (2025) . EURēCA: Exhibition of Undergraduate Research and Creative Achievement. [https://trace.tennessee.edu/eureca/16](https://trace.tennessee.edu/eureca/16)  \nThis Article is brought to you for free and open access by the Supervised Undergraduate Student Research and Creative Work at TRACE: Tennessee Research and Creative Exchange. It has been accepted for inclusion in EURēCA: Exhibition of Undergraduate Research and Creative Achievement by an authorized administrator of TRACE: Tennessee Research and Creative Exchange. For more information, please contact [trace@utk.edu](trace@utk.edu).  \nHigh School to NCAA: Predicting Freshman Impact in College Basketball  \nwith Machine Learning  \nAuthor: Timothy Held ( [theld1@vols.utk.edu](theld1@vols.utk.edu) ) Faculty Advisor: Adam Spannbauer ([aspannba@utk.edu](aspannba@utk.edu) )  \nCompany: Tennessee Men’s Basketball ( [garrett.medenwald@utk.edu](garrett.medenwald@utk.edu) )  \nBackground  \n• As of April 2025, judicial rulings have removed limitations and guidance related to name, image, and likeness (NIL) usage and compensation, transfer student eligibility, and school-athlete revenue sharing.  \n• Now, more than ever, athletic departments, teams, and coaches need to focus on financial roster management, transparent recruiting, and relationship building.  \n• NBA teams use free agent and draft models to make informed roster and budget management decisions .  \n•  Research Objective: Build a predictive tool to inform coaches on potential impact of high school players at high major schools (SEC-level) in their freshman year.  \nData:  \n• We partnered with Synergy Sports, a division of Sportsradar, to access their API to collect game and player data for the model  \n• We compiled 4 years of game-level statistics from high school summer leagues (AAU) and college basketball (NCAA)  \n• The data is composed of statistics in 5 main categories: Player aggregated box scores, team aggregated box scores, opponent aggregated box scores, league aggregated box scores, and player aggregated advanced statistics.  \n• The data totaled over 150 statistics for over 350 individual college freshman seasons . For modeling, this was reduced to near 70 variables.  \nMethodology:  \n•  Calculated Wins Above Replacement Player (WARP) for each season, highschool and college. WARP is a comprehensive measure of a player’s impact related to a “replacement-level player”.  \n• Using the AutoML package PyCaret, we constructed the below ensemble model, training on past data and testing model accuracy on current freshman .  \n\n| Predictive Model Name: | Predictive Model Type |\n| --- | --- |\n| Preliminary High-Major WARP Model | Gradient Boosted Regression (GBR):\u003Cbr>• 71 statistical inputs from high school\u003Cbr>• Outputs logged value of freshman year WARP |\n| Significant Contributor Model | K-Nearest Neighbors (KNN):\u003Cbr>• 71 statistical inputs from high school\u003Cbr>• Outputs probability of an incoming freshman playing 450 minutes (~40% of max possible minutes played) |\n| Major Contributor Model | K-Nearest Neighbors (KNN):\u003Cbr>• 71 statistical inputs from high school\u003Cbr>• Outputs probability of an incoming freshman playing 6","cbCaifFqX200Iv2r","https://ap.wps.com/l/cbCaifFqX200Iv2r","pdf",765802,1,2,"English","en",105,"# Background\n# Data\n# Methodology\n# Predictive Models\n## Preliminary High-Major WARP Model\n## Significant Contributor Model\n## Major Contributor Model\n## Stacked High-Major WARP Model\n# Results\n# Player Prediction Examples\n# Implementation","[{\"question\":\"What is the main goal of the project?\",\"answer\":\"To build a predictive tool that estimates potential freshman impact for high school players at high-major (SEC-level) college programs.\"},{\"question\":\"What data sources were used to train the models?\",\"answer\":\"The study uses an API from Synergy Sports and compiles four years of game-level statistics from high school summer leagues (AAU) and college basketball (NCAA).\"},{\"question\":\"How does the methodology measure player impact?\",\"answer\":\"It calculates Wins Above Replacement Player (WARP) for each season and models outcomes using a stacked ensemble approach built with AutoML (PyCaret).\"}]","High School to NCAA - Predicting Freshman Impact in College Basketball with Machine Learning | PDF",1785821270,5,{"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":85,"head_meta":87,"extra_data":89,"updated_unix":28},"high-school-to-ncaa-predicting-freshman-impact-in-college-basketball-with-machine-learning","",{"@graph":36,"@context":84},[37,53,67],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":21},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/high-school-to-ncaa-predicting-freshman-impact-in-college-basketball-with-machine-learning/124262/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What is the main goal of the project?","Question",{"text":74,"@type":75},"To build a predictive tool that estimates potential freshman impact for high school players at high-major (SEC-level) college programs.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What data sources were used to train the models?",{"text":79,"@type":75},"The study uses an API from Synergy Sports and compiles four years of game-level statistics from high school summer leagues (AAU) and college basketball (NCAA).",{"name":81,"@type":72,"acceptedAnswer":82},"How does the methodology measure player impact?",{"text":83,"@type":75},"It calculates Wins Above Replacement Player (WARP) for each season and models outcomes using a stacked ensemble approach built with AutoML (PyCaret).","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,108,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":29,"doc_module":4,"doc_module_name":46,"category_name":105,"show_sort_weight":106,"slug":107},"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":46,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":46,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":46,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":29,"slug":136},19,"General","general"]