[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-1-en-105":3,"doc-seo-177652-105":53,"doc-detail-177652-en":127},{"code":4,"msg":5,"data":6},0,"success",[7,14,19,24,29,34,39,44,49],{"id":8,"doc_module":9,"doc_module_name":10,"category_name":11,"show_sort_weight":12,"slug":13},11,1,"Template","Presentations",90,"presentations",{"id":15,"doc_module":9,"doc_module_name":10,"category_name":16,"show_sort_weight":17,"slug":18},12,"Resumes",80,"resumes",{"id":20,"doc_module":9,"doc_module_name":10,"category_name":21,"show_sort_weight":22,"slug":23},14,"Invoices",70,"invoices",{"id":25,"doc_module":9,"doc_module_name":10,"category_name":26,"show_sort_weight":27,"slug":28},15,"Posters",60,"posters",{"id":30,"doc_module":9,"doc_module_name":10,"category_name":31,"show_sort_weight":32,"slug":33},16,"Social Media",50,"social-media",{"id":35,"doc_module":9,"doc_module_name":10,"category_name":36,"show_sort_weight":37,"slug":38},17,"Forms",40,"forms",{"id":40,"doc_module":9,"doc_module_name":10,"category_name":41,"show_sort_weight":42,"slug":43},18,"Letters",30,"letters",{"id":45,"doc_module":9,"doc_module_name":10,"category_name":46,"show_sort_weight":47,"slug":48},21,"Paper Templates",5,"papers-templates",{"id":50,"doc_module":9,"doc_module_name":10,"category_name":51,"show_sort_weight":4,"slug":52},158,"General","general-158",{"code":4,"msg":54,"data":55},"ok",{"site_id":56,"language":57,"slug":58,"title":59,"keywords":60,"description":61,"schema_data":62,"social_meta":120,"head_meta":122,"extra_data":124,"updated_unix":126},105,"en","using-data-mining-to-predict-freshmen-outcomes","Using Data Mining to Predict Freshmen Outcomes","","Data mining models are developed to predict first-time, full-time freshmen GPA early in the college career, supporting timely interventions for students at risk. The study evaluates student engagement through service utilization and transactional evidence, including advising visits, course-taking activity, interactions with the learning management system, and participation in campus activities, alongside SAT scores, high school GPA, demographics, and financial aid. For first semester GPA prediction, campus interaction factors outperform SAT scores, indicating stronger linkage to freshmen success.",{"@graph":63,"@context":119},[64,80,102],{"@type":65,"itemListElement":66},"BreadcrumbList",[67,71,74,77],{"item":68,"name":69,"@type":70,"position":9},"https://docshare.wps.com","Home","ListItem",{"item":72,"name":10,"@type":70,"position":73},"https://docshare.wps.com/template/",2,{"item":75,"name":46,"@type":70,"position":76},"https://docshare.wps.com/template/paper-templates/",3,{"item":78,"name":59,"@type":70,"position":79},"https://docshare.wps.com/template/using-data-mining-to-predict-freshmen-outcomes/177652/",4,{"url":78,"name":59,"@type":81,"image":82,"author":87,"headline":59,"publisher":90,"fileFormat":93,"inLanguage":57,"description":61,"dateModified":94,"datePublished":95,"encodingFormat":93,"isAccessibleForFree":96,"interactionStatistic":97},"DigitalDocument",{"url":83,"@type":84,"width":85,"height":86},"https://docshare.wps.com/thumbnails/using-data-mining-to-predict-freshmen-outcomes/177652.png","ImageObject",442,249,{"name":88,"@type":89},"Bintang","Person",{"url":68,"name":91,"@type":92},"DocShare","Organization","application/vnd.openxmlformats-officedocument.wordprocessingml.document","2026-10-07","2026-09-02",true,{"@type":98,"interactionType":99,"userInteractionCount":101},"InteractionCounter",{"@type":100},"ViewAction",8,{"@type":103,"mainEntity":104},"FAQPage",[105,111,115],{"name":106,"@type":107,"acceptedAnswer":108},"What is the primary purpose of the data mining model in this study?","Question",{"text":109,"@type":110},"To predict at-risk first-time, full-time freshmen as early as possible so institutions can support effective interventions.","Answer",{"name":112,"@type":107,"acceptedAnswer":113},"Which predictors are included beyond traditional academic factors?",{"text":114,"@type":110},"The models include service utilization and transactional data such as advising visits, freshmen course-taking activity, learning management system interactions, and participation in campus activities, along with SAT scores, high school GPA, demographics, and financial aid.",{"name":116,"@type":107,"acceptedAnswer":117},"How do campus interaction factors compare with SAT scores for predicting first semester GPA?",{"text":118,"@type":110},"Campus interaction factors are stronger predictors than SAT scores in models predicting first semester freshmen GPA.","https://schema.org",{"og:url":78,"og:type":121,"og:title":59,"og:site_name":91,"og:description":61},"article",{"robots":123,"canonical":78},"index,follow",{"doc_id":125,"site_id":56},177652,1788328736,{"code":4,"msg":5,"data":128},{"doc_id":125,"user_id":129,"nickname":88,"user_avatar":130,"doc_module":9,"category_id":45,"category_name":46,"doc_title":59,"doc_description":61,"doc_content":131,"file_id":132,"file_url":133,"file_type":134,"file_size":135,"view_count":101,"is_deleted":4,"is_public":9,"is_downloadable":9,"audit_status":9,"page_count":136,"language":137,"language_code":57,"site_id":56,"html_lang":57,"table_of_contents":138,"faqs":139,"seo_title":140,"seo_description":61,"update_tm":126,"read_time":141},962085564381,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","USING DATA MINING TO PREDICT FRESHMEN OUTCOMES\nNora Galambos, PhD Senior Data Scientist\nOffice of Institutional Research, Planning & Effectiveness Stony Brook University\nAbstract\nData mining is used to develop models for the early prediction of freshmen GPA. Since student engagement has long been associated with student success, the use of service utilization and transactional data is examined along with more traditional student factors. Factors entered into the data mining models include advising visits, freshmen course-taking activity, interactions with the college learning management system, and college activity participation, along with SAT scores, high school GPA, demographics, and financial aid. In models predicting first semester freshmen GPA, factors associated with students' interactions with the campus environment were stronger predictors than SAT scores.\nIntroduction\nThe goal is to develop a model to predict at risk first-time full-time freshmen as early as possible in their college careers in order to assist them with interventions. Traditional methods of logistic and linear regression are often good at identifying factors significantly associated with an outcome, but are not always able to make accurate predictions. Linear and logistic regression have one set of predictors to model the outcomes of all of the students in the data and do not assign separate sets of predictors to students having very different characteristics. For example,\nfirst-time freshmen entering college with high SAT scores may have very different retention and college GPA predictors than those entering with a low high school GPA and low SAT scores.\nInevitably, when using any model, some students will be incorrectly assigned, with some students miss-identified as being at risk or students at risk being not being identified as such by the model. There is an allocation trade-off when resources are expended on students not really in need of interventions or when students who would potentially benefit from interventions do not receive them. Methods capable of more accurate predictions will result in more effective utilization of resources, and higher retention and graduation rates. For that reason the decision was made to explore data mining, because it offers a variety of methods for utilizing different types of data, there are few assumptions to satisfy relative to traditional hypothesis driven methods, and it is able to handle a great volume of data with hundreds of predictors.\nAt our institution poor academic performance by first-time full-time freshmen in the first semester has a negative impact on graduation and retention outcomes. Figure 1 illustrates that only 11% of students in the lowest GPA decile graduate in four years, and less than 29% of students in that group graduate in six years. For the second decile the four year rate increases to 26% and the six year rate improves to 53%. Those rates, though higher, are still very low relative to the top half of the freshmen class.\nApproximately 30% of first-time full-time freshmen received a GPA below 2.5 in their first semester (Figure 2). Almost 84% of those students returned in year two, however by the next year the retention rate had dropped substantially with only 64% returning for year three and only 48% graduating in six years. In contrast over 77% of students receiving a GPA of 2.5 or greater in their first semester graduated in six years.\nPercent Graduated\nFigure 1. Four and Six Year Graduation Rates of First-Time Full-Time Freshmen by GPA Deciles*\n*The fall freshmen cohorts of 2006 through 2008 were combined.\nFigure 2. Comparison of Graduation and Retention Rates of First-time Full-time Freshmen by First Semester GPA Above and Below 2.5.\n*The fall freshmen cohorts of 2006 through 2008 were combined.\nEven when evaluating results for students above and below 3.0 the differences are dramatic (Figure 3). Only 34% of students with a first semester GPA below 3.0 (approximately the median) ","cbCaic7kM3im4yoK","https://ap.wps.com/l/cbCaic7kM3im4yoK","docx",478566,26,"English","# Introduction\n## Prediction goal and intervention allocation trade-off\n## Limitations of logistic and linear regression\n## Graduation and retention patterns by GPA deciles\n## Early identification using transactional and service utilization data\n## Literature review: campus engagement and risk factors","[{\"question\":\"What is the primary purpose of the data mining model in this study?\",\"answer\":\"To predict at-risk first-time, full-time freshmen as early as possible so institutions can support effective interventions.\"},{\"question\":\"Which predictors are included beyond traditional academic factors?\",\"answer\":\"The models include service utilization and transactional data such as advising visits, freshmen course-taking activity, learning management system interactions, and participation in campus activities, along with SAT scores, high school GPA, demographics, and financial aid.\"},{\"question\":\"How do campus interaction factors compare with SAT scores for predicting first semester GPA?\",\"answer\":\"Campus interaction factors are stronger predictors than SAT scores in models predicting first semester freshmen GPA.\"}]","Using Data Mining to Predict Freshmen Outcomes | DOCX",9]