[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119844-en":3,"doc-seo-119844-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},119844,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Low-achievement risk assessment with machine learning","A method is proposed to assess the risk of low-achievement in secondary school using data collected from the Italian ministry of education. Low-achievement is framed as students completing schooling without reaching the competence level expected by the school system. Three machine learning models are trained on INVALSI large-scale assessment test data and compared for predictive and descriptive performance. End-of-primary mathematics test data are used to estimate risk at the end of compulsory schooling, years later, with promising results supporting generalization across school systems and subjects.","Low-achievement risk assessment with machine learning  \nAndrea Zanellati1, * , Stefano P. Zingaro 1 and Maurizio Gabbrielli 1  \n1 Università di Bolonga, via Zamboni 33, Bologna, 40126, Italy  \nAbstract  \nIn this work, we propose a method for assessing the risk of low-achievement in secondary school with data collected from the Italian ministry of education. Low-achievement is a phenomenon whereby a student, despite completing his or her education, does not reach the level of competence expected by the school system. We train three machine learning models on a large, real dataset through the INVALSI large-scale assessment tests and compare the results in terms of predictive and descriptive performance. We exploit data collected in end-of-primary school mathematics tests to predict the risk of low-achievement atthe end of compulsory schooling (5 years later) . The promising results of our approach suggest that it is possible to generalise the methodology for other school systems and for different teaching subjects.  \nKeywords  \nlow-achievement, performance prediction, assessment test, machine learning  \n1. Introduction  \nLow-achievement at school is a widespread phenomenon which has long-term consequences, both for the individual and for society as a whole. In 2016, above 28% of students across Organization for Economic Co-operation and Development (OECD) countries underscored theminimum level of proficiency in at least one of the three core subjects according to the Programme for International Student Assessment (PISA), which are English reading and comprehension, mathematics, and science [1] . Lowachievement is strongly related to school dropout, i.e., the discontinuation of education [2], and impact on the cultural and professional growth of the individual and citizen [3, 4] . Indeed, school performance in first grade is already a significant indicator of future high dropout risk. In 2019, a study conducted by the National Institute for Assessment of the Education System (INVALSI) found that 20% percent of Italian students had a lower-thanexpected achievement and, eventually, dropped out of school [5] . This way, despite the exterior appearance and, in some cases, despite the sufficient marks, the students do not reach the adequate level of knowledge which later on will be needed to successfully continue the studies or to start a professional career. In this perspective, low achievement can be considered an “implicit” form of school dropout: although some students do not occur into explicit early leaving from school, the result is a lack  \nItal-IA 2023: 3rd National Conference on Artificial Intelligence, orga nized by CINI, May 29–31, 2023, Pisa, Italy  \n* Corresponding author.  \n$ [andrea.zanellati2@unibo.it](andrea.zanellati2@unibo.it) (A. Zanellati);  \n[stefano.zingaro@unibo.it](stefano.zingaro@unibo.it) (S. P. Zingaro);  \n[maurizio.zingaro@unibo.it](maurizio.zingaro@unibo.it) (M. Gabbrielli)  \n􀀚 0000-0001-6171-0397 (A. Zanellati); 0000-0002-8462-5651  \n(S. P. Zingaro); 0000-0003-0609-8662 (M. Gabbrielli)  \n© 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License  \n\n|  | CEUR Workshop Proceedings |\n| --- | --- |\n\nAttribution 4 .0 International (CC BY 4 .0) .  \nCEUR Workshop Proceedings ([CEUR-WS.org](CEUR-WS.org))  \n[http://ceur-ws.org](http://ceur-ws.org)  \n[ISSN 1613-0073](ISSN 1613-0073)  \nof school effect on their skills acquisition.  \nAn important indicator for school dropout is the ELET rate, which measures the percentage of Early Leavers from Education and Training [6] . It measures a severe condition of educational exclusion which refers to young people between 18 and 24 with a qualification lower than upper secondary. Early leavers from education and training are more likely to be unemployed or employed in low-paid jobs with few or no prospects for training and further career progression; they are more prone to social exclusion and to experience lower levels of health, wellbeing","cbCaicDAFFvPg9Kh","https://ap.wps.com/l/cbCaicDAFFvPg9Kh","pdf",1181874,1,5,"English","en",105,"# Introduction\n## Research questions and early-stage detection\n## Modeling approach and dataset focus","[{\"question\":\"What does low-achievement mean in this study?\",\"answer\":\"Low-achievement describes a student who completes education but does not reach the competence level expected by the school system.\"},{\"question\":\"Which data sources are used to build and test the machine learning models?\",\"answer\":\"The approach uses INVALSI large-scale assessment test data, with emphasis on mathematics results from end-of-primary school.\"},{\"question\":\"How is early risk of low-achievement predicted?\",\"answer\":\"Risk is detected several years in advance by training three models to predict the risk at K-10 using student data at K-5.\"}]","Low-achievement risk assessment with machine learning | PDF",1785726612,13,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"low-achievement-risk-assessment-with-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/low-achievement-risk-assessment-with-machine-learning/119844/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What does low-achievement mean in this study?","Question",{"text":75,"@type":76},"Low-achievement describes a student who completes education but does not reach the competence level expected by the school system.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which data sources are used to build and test the machine learning models?",{"text":80,"@type":76},"The approach uses INVALSI large-scale assessment test data, with emphasis on mathematics results from end-of-primary school.",{"name":82,"@type":73,"acceptedAnswer":83},"How is early risk of low-achievement predicted?",{"text":84,"@type":76},"Risk is detected several years in advance by training three models to predict the risk at K-10 using student data at K-5.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":21,"slug":137},19,"General","general"]