[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-581829-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-581829-en":131},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","a-machine-learning-approach-to-predicting-masters-degree-completion-at-the-university-of-texas-at-san-antonio","A Machine Learning Approach to Predicting Master’s Degree Completion at the University of Texas at San Antonio","","A study estimates determinants of timely master’s degree completion (within 3 years) using modern machine learning models including random forest, decision trees, extreme gradient boosting, gradient boosting, and AdaBoost. Using 15 years of master’s cohort data from the University of Texas at San Antonio, the research finds gradient boosting with hyperparameter tuning performs best, achieving over 80% correct predictions. Beyond GPA and enrollment status, the model highlights student loans, and department-level demographic-structural factors such as faculty count and gender and non-White representation.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/a-machine-learning-approach-to-predicting-masters-degree-completion-at-the-university-of-texas-at-san-antonio/581829/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/a-machine-learning-approach-to-predicting-masters-degree-completion-at-the-university-of-texas-at-san-antonio/581829.png","ImageObject",300,407,{"name":42,"@type":43},"Aurelia","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-15","2026-10-15",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",13,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Which machine learning models are used to predict timely master’s degree completion?","Question",{"text":63,"@type":64},"The study compares random forest, decision tree, extreme gradient boosting, gradient boosting, and AdaBoost to estimate timely completion within 3 years.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What model performs best in predicting 3-year master’s degree completion?",{"text":68,"@type":64},"Gradient boosting with hyperparameter tuning provides the best predictive performance, correctly predicting more than 80% of cases in the study.",{"name":70,"@type":61,"acceptedAnswer":71},"What factors are associated with higher likelihood of completing a master’s degree within 3 years?",{"text":72,"@type":64},"The model indicates students with higher GPAs, younger age, full-time enrollment, and those who took out student loans are more likely to graduate within 3 years.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},581829,1792193212,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":140,"language":141,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":12,"update_tm":145,"read_time":146,"preview_page_count":4},1099514068365,"https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?x-image-process=image/resize,m_fixed,w_180,h_180&k=1794309523707217728","A Machine Learning Approach to Predicting Master’s Degree Completion at the University of Texas at San Antonio  \nFikrewold Bitew and Lauren Apgar  \nAbout the Authors  \nFikrewold Bitew, PhD, and Lauren Apgar, PhD, have a combined 20 years of experience in the field of institutional research. They currently work in Institutional Research and Analysis at the University of Texas at San Antonio.  \nAcknowledgments  \nWe would like to thank the Institutional Research and Analysis team at the University of Texas at San Antonio for their feedback and suggestions. Thankyou to Khoi To for his insightful comments on an earlier draft of this manuscript.  \nAbstract  \nThe pursuit of a master’s degree is a significant academic endeavor, one that is influenced by a complex interplay of factors extending beyond traditional academic performance. In this study, we estimate the determinants of timely master’s degree completion (i. e., within 3 years) using modern machine learning models such as random forest, decision tree, extreme gradient boosting, gradient boosting, and AdaBoost. After analyzing 15  \nThe AIR Professional File, Winter 2025  \nArticle 176  \nyears of master’s cohort data from the University of Texas at San Antonio, a large, public, Hispanicserving university, our findings indicated that gradient boosting with hyperparameter tuning was a reasonably superior machine learning model for predicting master’s degree completion at our institution. The selected model accurately predicted more than 80% of the cases in the study and demonstrated superior predictive performance compared to the traditional logistic regression model. In support of nontraditional student retention theory, the model identified that students with higher GPAs, younger students, fulltime students, and students who took out student loans were more likely to graduate within 3 years than students with lower GPAs, older students, part-time students, and students without loans, respectively. Furthermore, demographic-structural components, which are often overlooked in machine learning models, proved to be important: students in departments with a larger number of faculty and higher representation of female and nonWhite faculty members had a greater likelihood of completing their master’s degree successfully.  \nKeywords: master’s students, 3-year completion, machine learning, gradient boosting  \n[https://doi.org/10.34315/apf1762025](https://doi.org/10.34315/apf1762025)  \nCopyright © 2025, Association for Institutional Research  \nWinter 2025 Volume 5  \nINTRODUCTION  \nThe number and percentage of the [U.S. adult](U.S. adult)[ ](U.S. adult)[population with graduate-level degrees have](population with graduate-level degrees have)[ ](population with graduate-level degrees have)[grown substantially over the past decade. Between](grown substantially over the past decade. Between)[ ](grown substantially over the past decade. Between)academic years 2011–12 and 2021–22, the number of master’s degrees awarded increased 16%, from 170,200 to 203,900 (National Center for Education Statistics, 2024) . Despite the growth in the number of master’s degrees conferred, the United States lacks nationwide data on which students begin a master’s program but do not complete it. State-level data suggest that non-completion is a critical issue for students seeking master’s degrees. For example, almost one-quarter (24%) of students seeking master’s degrees from public institutions in Texas do not complete their degree within 5 years, according to our (the authors’) analysis of data retrieved from the Texas Higher Education Coordinating Board (2022) Accountability System.  \nCompleting a master’s degree offers both advanced expertise in a field and increased earning potential. On average, graduate degree holders earn more than individuals with a 4-year degree (Pyne & Grodsky, 2020; Valletta, 2018) . Students take substantial risks in pursuing a graduate-level degree, however, since graduate and profess","cbCaif84zOnNeD15","https://ap.wps.com/l/cbCaif84zOnNeD15","pdf",455458,21,"English","# INTRODUCTION\n## Background on graduate-degree growth and completion gaps\n## Value and risks of pursuing master’s degrees\n## Motivation for using educational data mining and machine learning\n## Limitations in existing research and department-level considerations","[{\"question\":\"Which machine learning models are used to predict timely master’s degree completion?\",\"answer\":\"The study compares random forest, decision tree, extreme gradient boosting, gradient boosting, and AdaBoost to estimate timely completion within 3 years.\"},{\"question\":\"What model performs best in predicting 3-year master’s degree completion?\",\"answer\":\"Gradient boosting with hyperparameter tuning provides the best predictive performance, correctly predicting more than 80% of cases in the study.\"},{\"question\":\"What factors are associated with higher likelihood of completing a master’s degree within 3 years?\",\"answer\":\"The model indicates students with higher GPAs, younger age, full-time enrollment, and those who took out student loans are more likely to graduate within 3 years.\"}]","A Machine Learning Approach to Predicting Master’s Degree Completion at the University of Texas at San Antonio | PDF",1792041857,53]