[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-580218-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-580218-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","modelability-as-a-strategy-for-improving-the-generalizability-and-scalability-of-predictive-models-volume-13-abstract","Modelability as a Strategy for Improving the Generalizability and Scalability of Predictive Models - Volume 13 - Abstract","","Learning analytics promises data-informed education, yet persistent obstacles in generalizability and scalability restrict real-world impact across institutions. This paper proposes “modelability” as a strategy for designing learning ecosystems that intentionally support predictive models transferring across diverse contexts. Three design principles guide the approach: valid and interpretable measurements, scalable and stable implementation, and a collaborative research–practice–technology ecosystem. A CourseKata case study operationalizes these ideas and demonstrates effective cross-institution generalization.",{"@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/modelability-as-a-strategy-for-improving-the-generalizability-and-scalability-of-predictive-models-volume-13-abstract/580218/",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/modelability-as-a-strategy-for-improving-the-generalizability-and-scalability-of-predictive-models-volume-13-abstract/580218.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",6,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does the paper address in learning analytics?","Question",{"text":63,"@type":64},"It addresses persistent challenges that limit learning analytics impact, specifically difficulties in generalizability and scalability across educational contexts and institutions.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What is “modelability” in this paper?",{"text":68,"@type":64},"Modelability is a design strategy for learning ecosystems purposefully built to support predictive models that generalize across diverse contexts.",{"name":70,"@type":61,"acceptedAnswer":71},"How do the authors test the proposed approach?",{"text":72,"@type":64},"They use CourseKata data to develop early prediction models of students’ final course grades and evaluate generalizability across institutions in a cross-institution case study.","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},580218,1792209825,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,105,110,114,119,122,126],{"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":55,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},"Technology",50,"technology",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},7,"Healthcare",40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},8,30,"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":111,"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":145,"preview_page_count":4},7971461740886,"https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2","Volume 13(1), 89–109 . [https://doi.org/10.18608/jla.2026.9099](https://doi.org/10.18608/jla.2026.9099)  \nModelability as a Strategy for Improving the Generalizability and Scalability of Predictive Models  \nAlice Xu 1 , Icy (Yunyi) Zhang2 , Adam B. Blake3 and James W. Stigler4  \nAbstract  \nLearning analytics has the potential to enhance education through data-informed decision-making, but persistent challenges around generalizability and scalability continue to limit its real-world impact. In this paper, we introduce the concept of a modelable world: a learning ecosystem purposefully designed to support the development of predictive models that generalize across diverse contexts. We outline three core design principles of modelability:  \n(1) valid and interpretable measurements, (2) scalable and stable implementation, and (3) a collaborative research– practice–technology ecosystem. We then illustrate how these principles can be operationalized in the real world through a case study of CourseKata, a platform offering a fully instrumented online textbook adopted across a wide range of institutions and disciplines. Using CourseKata data, we developed early prediction models of students’ final course grades using behavioral measures and tested the model generalizability across institutions (something rarely done in the modeling literature) . Results show that a system designed with modelability in mind can produce predictive models that generalize effectively across diverse educational contexts.  \n\n| Notes for Practice\u003Cbr>• Predictive modeling in learning analytics often struggles with generalizability and scalability due to variations in context, data availability, and implementation across institutions.\u003Cbr>• This paper introduces modelability as a design strategy for creating learning ecosystems that enable the development of predictive models that are both generalizable and scalable, demonstrated through a cross-institutional case study using CourseKata.\u003Cbr>• The findings suggest that intentionally designed, instrumented learning platforms can support the development of early interventions by enabling predictive models that transfer effectively across diverse educational contexts. |\n| --- |\n| Keywords: Modelability, generalizability, scalability, cross-institutional research , predictive learning analytics\u003Cbr>Submitted: 04/06/2025—Accepted: 30/12/2025—Published: 14/03/2026 |\n\nCorresponding author 1Email: [alicex@g.ucla.edu](alicex@g.ucla.edu) Address: Department of Psychology, University of California, Los Angeles (UCLA), 1285 Franz  \nHall Box 951563, Los Angeles, CA 90095, USA. ORCID iD: [https://orcid.org/0000-0001-8111-0700](https://orcid.org/0000-0001-8111-0700)  \n2Email: [icy.zhang@wisc.edu](icy.zhang@wisc.edu) Address: Department of Educational Psychology, University of Wisconsin–Madison, 1025 W Johnson St, Madison, WI 53706, USA. ORCID iD: [https://orcid.org/0000-0003-3423-6794](https://orcid.org/0000-0003-3423-6794)  \n3Email: [adam@coursekata.org](adam@coursekata.org) Address: Fund for the City of New York, 121 Avenue of the Americas, 6th F1, New York, NY 10013, USA. ORCID  \niD: [https://orcid.org/0000-0001-7881-8652](https://orcid.org/0000-0001-7881-8652)  \n4Email: [stigler@ucla.edu](stigler@ucla.edu) Address: Department of Psychology, University of California, Los Angeles (UCLA), 1285 Franz Hall Box 951563, Los  \nAngeles, CA 90095, USA. ORCID iD: [https://orcid.org/0000-0001-6107-7827](https://orcid.org/0000-0001-6107-7827)  \n1. Introduction  \nOnline learning has transformed education by making learning more accessible, leading to growing adoption, and offering new ways to understand the learning process. Meanwhile, it also generates vast amounts of learner data that can be captured, interpreted, and effectively used to enhance educational practices. In response, the field of learning analytics (LA) has emerged, focusing on “the measurement, collection, analysis, and reporting of data about learners and their contexts","cbCaihZUdgKMzW0h","https://ap.wps.com/l/cbCaihZUdgKMzW0h","pdf",1596141,23,"English","# Abstract\n## Notes for Practice\n## Keywords\n## Introduction\n### The Generalizability Issue in Learning Analytics","[{\"question\":\"What problem does the paper address in learning analytics?\",\"answer\":\"It addresses persistent challenges that limit learning analytics impact, specifically difficulties in generalizability and scalability across educational contexts and institutions.\"},{\"question\":\"What is “modelability” in this paper?\",\"answer\":\"Modelability is a design strategy for learning ecosystems purposefully built to support predictive models that generalize across diverse contexts.\"},{\"question\":\"How do the authors test the proposed approach?\",\"answer\":\"They use CourseKata data to develop early prediction models of students’ final course grades and evaluate generalizability across institutions in a cross-institution case study.\"}]","Modelability as a Strategy for Improving the Generalizability and Scalability of Predictive Models - Volume 13 - Abstract | PDF",1792037177,58]