[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-580176-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-580176-en":130},{"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","unpacking-the-black-box-a-hybrid-xai-framework-for-autogluon-based-multiclass-student-outcome-prediction","Unpacking the Black Box - A Hybrid XAI Framework for AutoGluon-Based Multiclass Student Outcome Prediction","","High student dropout rates obstruct progress toward UN SDG 4 (equitable education). Although AI enables early risk prediction, high-performing models are often opaque, limiting transparency. This study proposes a multi-layer Explainable AI assessment framework for student retention using AutoGluon to build multiclass models (Graduated, Dropout, Enrolled). A hybrid XAI strategy combines global decision-tree surrogates and local LIME explanations. Results show Boosting methods, especially XGBoost with bagging level 2, achieve strong performance and highlight key academic and socio-economic drivers.",{"@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/unpacking-the-black-box-a-hybrid-xai-framework-for-autogluon-based-multiclass-student-outcome-prediction/580176/",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/unpacking-the-black-box-a-hybrid-xai-framework-for-autogluon-based-multiclass-student-outcome-prediction/580176.png","ImageObject",300,407,{"name":42,"@type":43},"Theodore","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-16","2026-10-15",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",8,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does the study address regarding student retention?","Question",{"text":63,"@type":64},"The study targets high student dropout rates that hinder equitable education under SDG 4 and notes that common assessment approaches are often too late to intervene.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How does the framework make AutoGluon multiclass models explainable?",{"text":68,"@type":64},"It uses a hybrid XAI approach: a global decision-tree surrogate for overall interpretability and LIME for local, case-specific explanations of risk drivers.",{"name":70,"@type":61,"acceptedAnswer":71},"Which model achieved the best predictive performance, and what drivers were identified?",{"text":72,"@type":64},"Boosting models, particularly XGBoost with bagging level 2, achieved the highest performance. Global analysis emphasizes academic factors and also highlights socio-economic influences such as tuition fees, while local analysis links dropout to first-year challenges and enrollment age.","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},580176,1792208695,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,114,119,122,126],{"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":55,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":55,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"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":144,"read_time":112,"preview_page_count":4},7971461740886,"https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2","UNPACKING THE BLACK BOX: A HYBRID XAI FRAMEWORK FOR AUTOGLUON-BASED MULTICLASS STUDENT OUTCOME PREDICTION  \nABSTRACT  \nHigh student dropout rates remain a significant impediment to achieving the United Nations SDG 4 (equitable education) . While Artificial Intelligence (AI) offers robust early risk prediction, the intrinsic black-box nature of high-performing models constrains their transparency. This study designsand investigates a multi-layered Explainable AI (XAI)-based assessment framework to generate actionable insights for student retention. We utilized AutoGluon to construct high-performing multiclass classification models (Graduated, Dropout, or Enrolled) on a higher education dataset. To address the complexity of the AutoGluon-generated models, we employed a hybrid XAI framework that couples global interpretability via a decision tree surrogate model and local interpretability via LIME (Local Interpretable Model-agnostic Explanations) . The analysis revealed that models from the Boosting family, particularly XGBoost with bagging level 2, achieved the highest predictive performance (exceeding 0.890 across all metrics) . The global analysis demonstrated that academic factors were the primary drivers of prediction, but critical socio-economic factors, such as Tuition fees, also exerted significant influence. Local LIME analysis provided granular, case-specific insights, strongly linking dropout status to first-year academic challenges and to features such as age at enrollment. This integrated XAI approach transforms complex models into an interpretable system, supporting student retention and educational equity (SDG 4) .  \nKEYWORDS  \nAutoGluon, educational efficiency, Explainable AI (XAI), machine learning, SDG 4, student dropout prediction  \nHOW TO CITE  \nNawae M., Chankua S., Longsaman M. (2026)‘Unpacking the Black Box: A Hybrid XAI Framework for AutoGluon-Based Multiclass Student Outcome Prediction’, Journal on Efficiency and Responsibility in Education and Science, vol. 19, no. 1, pp. 28–39. [http://](http://)[ ](http://)[dx.doi.org/10.7160/eriesj.2026.190103](dx.doi.org/10.7160/eriesj.2026.190103)  \nFull research paper  \nMarwan Nawae* Siripa Chankua Massaya Longsaman  \nFaculty of Education and Liberal Arts, Hatyai University, Thailand  \n* [marwan.n@hu.ac.th](marwan.n@hu.ac.th)  \nArticle history Received  \nOctober 31, 2025  \nReceived in revised form  \nMarch 8, 2026  \nAccepted  \nMarch 9, 2026  \nAvailable on-line  \nMarch 31, 2026  \nHighlights  \n• A hybrid XAI framework interprets complex AutoML for multiclass prediction.  \n• Boosting model (XGBoost) achieved the highest performance (Accuracy > 0.890).  \n• Global analysis confirms that academic and socio-economic factors are the primary drivers.  \n• Local analysis provides granular, case-specific insights into each class for intervention.  \nINTRODUCTION  \nThe pursuit of equitable and inclusive education directly addresses the United Nations Sustainable Development Goal 4 (SDG 4). SDG 4 mandates high-quality, inclusive, and equitable education, promoting lifelong learning opportunities for all. However, achieving this remains challenging due to persistent inequalities in tertiary education. According to the Education ata Glance 2025: OECD Indicators report (OECD, 2025), unequal opportunities significantly hinder the educational attainment of learners from disadvantaged backgrounds. On average across OECD countries, only 26% of young adults whose parents did not complete upper secondary education hold a tertiary  \nqualification. Low completion rates compound this access gap. Newly collected data from over 30 countries show that only 43% of new bachelor’s students graduate within the expected duration. Even with three additional years, the completion rate only reaches 70%(OECD, 2025) . This high attrition rate disproportionately affects marginalized groups and acts asa major impediment to inclusivity. Beyond academic failure, the socioeconomic consequences are profound. Re","cbCaidhnHuhb6imr","https://ap.wps.com/l/cbCaidhnHuhb6imr","pdf",1751450,12,"English","# Abstract\n# Keywords\n# How to Cite\n# Article history\n# Highlights\n# Introduction\n## Equitable and inclusive education and SDG 4\n## Educational efficiency and assessment needs\n## Machine learning approaches and black-box limitations","[{\"question\":\"What problem does the study address regarding student retention?\",\"answer\":\"The study targets high student dropout rates that hinder equitable education under SDG 4 and notes that common assessment approaches are often too late to intervene.\"},{\"question\":\"How does the framework make AutoGluon multiclass models explainable?\",\"answer\":\"It uses a hybrid XAI approach: a global decision-tree surrogate for overall interpretability and LIME for local, case-specific explanations of risk drivers.\"},{\"question\":\"Which model achieved the best predictive performance, and what drivers were identified?\",\"answer\":\"Boosting models, particularly XGBoost with bagging level 2, achieved the highest performance. Global analysis emphasizes academic factors and also highlights socio-economic influences such as tuition fees, while local analysis links dropout to first-year challenges and enrollment age.\"}]","Unpacking the Black Box - A Hybrid XAI Framework for AutoGluon-Based Multiclass Student Outcome Prediction | PDF",1792037094]