[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-210714-en":3,"doc-seo-210714-105":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},210714,8796095461610,"Oliver","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Unveiling Patterns in Maranhão’s 2023 ENEM Results Through Unsupervised Machine Learning","This investigation examines the performance of students from Maranhão, Brazil, in the 2023 edition of the National High School Exam (ENEM) using unsupervised machine learning to uncover latent patterns in large-scale educational data. Leveraging the CRISP-DM framework on microdata from millions of ENEM participants, a hybrid pipeline combines Recursive Feature Elimination (RFE) with Random Forest and association rule mining via FP-Growth. Results reveal strong associations between low academic performance and socioeconomic and access-related factors, supporting targeted policy-making and equity monitoring.","Revista Brasileira de Informática na Educação – RBIE Brazilian Journal of Computers in Education (ISSN online: 2317-6121; print: 1414-5685)  \n[https://sol.sbc.org.br/journals/index.php/rbie](https://sol.sbc.org.br/journals/index.php/rbie)  \n\n| Submission: 08/07/2025;\u003Cbr>Camera ready: 23/03/2026; | 1st round notif.: 27/09/2025;\u003Cbr>Edition review: 02/04/2026; | New version: 26/11/2025;\u003Cbr>Available online: 02/04/2026; | 2nd round notif.: 18/12/2025;\u003Cbr>Published: 02/04/2026; |\n| --- | --- | --- | --- |\n\nUnveiling Patterns in Maranhão’s 2023 ENEM Results Through  \nUnsupervised Machine Learning  \nAnderson Amorim Alves  \nPrograma de Pós-Graduação em  \nEngenharia da Computação e Sistemas (PECS) Universidade Estadual do Maranhão (UEMA) ORCID: 0009-0005-9785-8365  \n[slz.anderson.ma@gmail.com](slz.anderson.ma@gmail.com)  \nOmar Andres Carmona Cortes Departamento de Computação (DComp) Instituto Federal do Maranhão (IFMA)  \nORCID: 0000-0002-5805-2490 [omar@ifma.edu.br](omar@ifma.edu.br)  \nAbstract  \nThis investigation examines the performance of students from Maranhão, Brazil, in the 2023 edition of the National High School Exam (ENEM) using unsupervised machine learning to uncover latent patterns in large-scale educational data. Leveraging the CRISP-DM framework on microdata from millions of ENEM participants, we applied Recursive Feature Elimination (RFE) with a Random Forest classifier to select key socioeconomic variables, followed by association rule mining using the FP-Growth algorithm across multiple experimental configurations. The results  \nreveal strong associations between low academic performance and factors such as parental education and occupa tion, lack of household technology (e.g., computers and washing machines), and gender. These findings demonstrate the utility of unsupervised learning for descriptive educational analytics, providing practical insights for targeted policy-making, resource allocation, and regional equity monitoring. This research addresses the underrepresentation of Maranhão in the educational data mining literature and proposes a scalable analytical framework applicable to  \nother developing regions. Despite limitations in data completeness, the approach offers a replicable model for using artificial intelligence to inform public education strategies in socially vulnerable areas.  \nKeywords: Educational Data Mining; Unsupervised Machine Learning; Pattern Discovery; Association Rules; ENEM  \nCite as: Alves, A. A., & Cortes, O. A. C. (2026). Unveiling Patterns in Maranhão’s 2023 ENEM Results Through Unsupervised Machine Learning. Revista Brasileira de Informática na Educação, vol. 34, pp. 404–428. [https://doi.org/10.5753/rbie.2026.6215](https://doi.org/10.5753/rbie.2026.6215).  \n1 Introduction  \nThe state of Maranhão in Brazil emerges as the object of study in this analysis, with a challenging scenario depicted by student performance in the ENEM, the results achieved in the Basic Education Development Index (IDEB), and a student body served mainly by the state public education network (Inep, 2024a) . Furthermore, the scarcity of educational studies that include the state of Maranhão and utilize the ENEM database may be relevant for investigating other influential variables for performance (Dutra et al., 2023) . In this context, the following research question: How are socioeconomic attributes, such as family income, parental education, access to technology (computers and internet), and gender, associated with the performance of Maranhão students in the 2023 ENEM?  \nThe study’s objective is to investigate the factors related to the performance of Maranhão students in the 2023 National High School Exam (ENEM) from the perspective of Educational Data Mining using Recursive Feature Elimination (RFE) with Random Forest to select the most critical variables, followed by association rule mining via FP-Growth algorithm. Evaluation metrics, including support, confidence, and lift, ensure the interpretability and","cbCaim2sQCdBVHu6","https://ap.wps.com/l/cbCaim2sQCdBVHu6","pdf",2201024,1,25,"English","en",105,"# Introduction\n## Related background and research question\n## Objective and methodology overview\n## Contributions and article structure","[{\"question\":\"What data and analytical approach are used to study Maranhão’s ENEM results?\",\"answer\":\"The study uses 2023 ENEM microdata from participants in Maranhão and applies a CRISP-DM driven workflow combining RFE with a Random Forest for variable selection, then association rule mining with FP-Growth.\"},{\"question\":\"Which factors are found to be strongly associated with low academic performance?\",\"answer\":\"The results indicate strong associations with parental education and occupation, limited household technology such as computers and washing machines, and gender-related differences.\"},{\"question\":\"Why does the study use FP-Growth instead of Apriori?\",\"answer\":\"FP-Growth is selected for efficiency on large transactional datasets like ENEM, requiring fewer database scans and avoiding candidate generation.\"}]","Unveiling Patterns in Maranhão’s 2023 ENEM Results Through Unsupervised Machine Learning | PDF",1788669626,63,{"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},"unveiling-patterns-in-maranhaos-2023-enem-results-through-unsupervised-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/unveiling-patterns-in-maranhaos-2023-enem-results-through-unsupervised-machine-learning/210714/",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","2026-09-06",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 data and analytical approach are used to study Maranhão’s ENEM results?","Question",{"text":75,"@type":76},"The study uses 2023 ENEM microdata from participants in Maranhão and applies a CRISP-DM driven workflow combining RFE with a Random Forest for variable selection, then association rule mining with FP-Growth.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which factors are found to be strongly associated with low academic performance?",{"text":80,"@type":76},"The results indicate strong associations with parental education and occupation, limited household technology such as computers and washing machines, and gender-related differences.",{"name":82,"@type":73,"acceptedAnswer":83},"Why does the study use FP-Growth instead of Apriori?",{"text":84,"@type":76},"FP-Growth is selected for efficiency on large transactional datasets like ENEM, requiring fewer database scans and avoiding candidate generation.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]