[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-125975-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-125975-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","machine-learning-algorithms-for-early-predicting-dropout-student-online-learning","Machine Learning Algorithms for Early Predicting Dropout Student Online Learning","","Online learning requires student self-management because activities in a Learning Management System (LMS) lack direct lecturer supervision. This independence increases the risk of dropout, making timely support essential. The study builds an early dropout prediction system using LMS access log data and student statistical information, comparing four machine learning models. Results show the Support Vector Machine achieving the highest accuracy (0.99) and strong F1-score (0.97), enabling lecturers and administrators to target at-risk students for prompt interventions.",{"@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/machine-learning-algorithms-for-early-predicting-dropout-student-online-learning/125975/",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/machine-learning-algorithms-for-early-predicting-dropout-student-online-learning/125975.png","ImageObject",300,407,{"name":42,"@type":43},"Liam","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-18","2026-08-05",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",15,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Why does online learning tend to have a higher dropout risk?","Question",{"text":63,"@type":64},"Online learning relies more on student self-control because learning activities are not supervised in the same way as in a classroom. Students must manage their study time independently, which contributes to dropout risk.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What data sources does the dropout prediction study use?",{"text":68,"@type":64},"The system uses access log data recorded in the LMS and student statistical information. These inputs support analysis and model training for early prediction.",{"name":70,"@type":61,"acceptedAnswer":71},"Which machine learning algorithm performed best in the study?",{"text":72,"@type":64},"The Support Vector Machine achieved the highest accuracy (0.99) and F1-score (0.97). Logistic Regression with Lasso showed the highest precision, while Naive Bayes(1) had the highest recall among the compared algorithms.","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},125975,1785902340,{"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":22,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":80,"read_time":30},687207024478,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","Sucianna Ghadati RabihaInformation Systems Department,BINUS Online LearningBina Nusantara UniversityJakarta,Indonesia 11480Sucianna.rabiha@binus.ac.id  \nAbstract—Online learning is different from offline learningin the classroom with supervision from the lecturer.Onlinelearning using the Learning Management System (LMS)mediarequires high awareness from students because their learningactivities are not supervised,they are free to study wherever andwhenever,so they need to manage and control their own studytime without the help of lecturers or administratorsThis is oneof the causes of the high dropout rate among online learningstudents,so it is very important for lecturers and administratorsto support students in a timely manner to avoid the risk ofdropping out.This study uses access log data recorded in theLMS and student statistical information and calculated dataand aims to present a suitable predictive algorithm for dropoutearly prediction systems for online learning students usingmachine learning.Of the 4 algorithms used,the highest recallvalue is in Naive Bayes(1),the highest precision is in LogisticRegression with Lasso(1),while the highest accuracy value  \n(0.99)and F1score(0.97)are obtained from the Support VectorMachine which has value equal to Logistic Regression withLasso.In general,the early dropout prediction model will allowlecturers and administrators to focus on students who have thepotential to dropout and take quick action to improve theirlearning performance so as to reduce the number of studentdropouts.  \nKeywords—Predictions,student,dropout,online learning,machine learning.  \n# I.  INTRODUCTION\n\nOnline learning is the best choice for students who arebusy working to learn new knowledge and earn a degreewithout any time or space constraints.And when the SARS-Cov-2 virus spread rapidly to become a pandemic,alluniversities changed offline or face-to-face learning methodsto online to avoid transmission of the virus between studentsand teachers [1].Given the time management of students andunsupervised educational activities in online learning,they arerequired to have the responsibility to complete their studiesindependently,in fact there are many cases of studentsdropping out [2],of course this is a challenge for universitiesproviding online learning.Active intervention from lecturersor managers is needed for students who have the potential todropout.  \nMeta Amalya DewiInformation Systems DepartmentBINUS Online LearningBina Nusantara UniversityJakarta,Indonesia 11480meta.dewi@binus.edu  \n2023 IEE 9th Interational Conference on Computing Enginering and Design (ICCED)|979-8-3503-7012-6/23/S31.002023 EEE| DO1:10.1109ICCED60214.2023.10425359  \nMachine Learning Algorithms for Early PredictingDropout Student Online Learning  \nFelix Indra KurniadiComputer Science DepartmentSchool of Computer ScienceBina Nusantara UniversityJakarta,Indonesia 11480felix.kurniadi@binus.edu  \nAwanis RomliFaculty of Computing,Universiti Malaysia Pahang,Pahang,Malaysiaawanis@ump.edu.my  \nFor this reason,universities providing online learningmust improve the analytic system for learning so that studentswho have the potential to drop out of school can be found asearly as possible and then provide appropriate interventionsobtained from the results of the analysis of student behaviourrecorded in the LMS [3].This prediction helps lecturers oradministrators take appropriate actions to improve learningoutcomes,so as to increase student graduation rates,helpuniversities make appropriate learning strategies,and providecritical feedback to students and lecturers [4].  \nThe prediction algorithm is used to produce predictionswith a high degree of accuracy in identifying students whohave low achievements and have the potential to dropout.Ittakes student datasets from LMS to be analysed and somemachine learning models are used for predictions.Machinelearning offers advantages over traditional statistical analysismethods.Predictive models are developed usin","cbCaiqJwsRSvTcXe","https://ap.wps.com/l/cbCaiqJwsRSvTcXe","pdf",207691,"English","# Introduction\n## Motivation and problem of online learning dropout\n## Need for early intervention\n# Method and data basis\n## LMS access log data and student information\n# Machine learning approach\n## Algorithm comparison and evaluation metrics\n# Results and implications\n## Accuracy, precision, recall, and F1-score insights\n## How early prediction supports learning outcomes and retention","[{\"question\":\"Why does online learning tend to have a higher dropout risk?\",\"answer\":\"Online learning relies more on student self-control because learning activities are not supervised in the same way as in a classroom. Students must manage their study time independently, which contributes to dropout risk.\"},{\"question\":\"What data sources does the dropout prediction study use?\",\"answer\":\"The system uses access log data recorded in the LMS and student statistical information. These inputs support analysis and model training for early prediction.\"},{\"question\":\"Which machine learning algorithm performed best in the study?\",\"answer\":\"The Support Vector Machine achieved the highest accuracy (0.99) and F1-score (0.97). Logistic Regression with Lasso showed the highest precision, while Naive Bayes(1) had the highest recall among the compared algorithms.\"}]","Machine Learning Algorithms for Early Predicting Dropout Student Online Learning | PDF"]