[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122388-en":3,"doc-seo-122388-105":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":4,"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},122388,962075114765,"Quinn","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Posita Data and Imbalanced Data Handling - A Case Study","A predictive machine learning model is developed to classify divorce verdicts (“Granted” or “Rejected”) in Indonesia’s Religious Courts using real posita narratives. The dataset includes 2,026 finalized divorce cases from the Religious Court of Padang Sidempuan (2018–2025), combining structured variables with plaintiff factual text. Keyword-based feature extraction converts narratives into interpretable indicators, and SMOTE addresses class imbalance in training. Six algorithms are evaluated via accuracy, precision, recall, F1/F2, and AUC, with Naïve Bayes achieving the highest recall for “Granted” while LightGBM and XGBoost show balanced performance.","International Journal of Advances in Data and Information Systems  \nVol. 6, No. 2, August 2025, pp. 460~478  \nISSN: 2721-3056, DOI: 10.59395/ijadis.v6i2.1405 r 460  \n\n| Posita Data and Imbalanced Data Handling: A Case Study inPadang Sidempuan  \u003Cbr>Rina Rahmadini1, Bagus Jati Santoso2  \u003Cbr>1,2School of Interdisciplinary Management and Technology, Institut Teknologi Sepuluh NopemberSurabaya, Indonesia   |  |\n| --- | --- |\n| Article Info  \u003Cbr>Article history:  \u003Cbr>Received May 29, 2025Revised Jul 18, 2025Accepted Aug 19, 2025  \u003Cbr>Keywords:  \u003Cbr>Machine Learning,Court Verdict Prediction,Divorce Case Analysis,Posita Data,  \u003Cbr>Imbalanced Data Handling  \u003Cbr>Corresponding Author:   | ABSTRACT  \u003Cbr>This study aims to develop a predictive model for divorce verdicts(\"Granted\" or \"Rejected\") in the Religious Courts of Indonesia usingmachine learning techniques. The dataset consists of 2,026 finalized divorcecases from the Religious Court of Padang Sidempuan between 2018 and2025, incorporating structured variables and posita—narrative textsdescribing the plaintiff’s reasons for divorce. Keyword-based featureextraction was applied to transform these texts into interpretable indicators.To handle class imbalance, Synthetic Minority Over-sampling Technique(SMOTE) was implemented on the training data. Six classical machinelearning algorithms were evaluated: Decision Tree, Naïve Bayes, K-NearestNeighbors, Random Forest, LightGBM, and XGBoost. Performance wasmeasured using accuracy, precision, recall, F1-score, F2-score, and AUC.The results indicate that Naïve Bayes achieved the highest recall (100%) forthe “Granted” class, while LightGBM and XGBoost demonstrated the mostbalanced performance across both classes. Feature importance analysisrevealed that mediation outcomes, domestic violence, and economic hardshipwere among the most influential factors in determining verdicts. The studyhighlights the applicability of interpretable machine learning in legal decisionsupport and discusses limitations such as the single-court scope andchallenges in predicting minority class outcomes. Future work may exploremulti-jurisdictional data, deep learning approaches, and domain-specificembeddings for enhanced performance.  \u003Cbr>This is an open access article under theCC BY-SAlicense.  \u003Cbr>   |\n| Rina Rahmadini,  \u003Cbr>School of Inter Interdisciplinary Management and Technology,  \u003Cbr>Institut Teknologi Sepuluh Nopember,  \u003Cbr>Kampus ITS Tjokroaminoto Jl. Cokroaminoto No. 12A, Tegalsari, Surabaya 60264, IndonesiaEmail: 6032231236@student.its.ac.id   |  |\n\n# 1. INTRODUCTION\n\nDivorce cases in Indonesia have shown a significant increase over the years. According to datafrom the Central Bureau of Statistics (BPS), the national divorce rate reached more than 516,000cases in 2022—marking the highest figure in the past seven years [1] . This phenomenon reflectsthe increasingly complex social dynamics of society and the growing workload of judicialinstitutions, particularly the Religious Courts, which have jurisdiction over family law cases underIslamic law in Indonesia [2] .  \nFigure 1. Number of divorce cases in Indonesia from 2016 to 2023 based on data from BPS [1] .  \nThe high volume of divorce cases urges the courts to seek innovative solutions to improvedecision-making efficiency and consistency. In the era of the Fifth Industrial Revolution (Industry  \n5.0), there is a growing opportunity to integrate intelligent technologies into the Indonesian judicialsystem to support decision-making processes [3] . Machine Learning (ML), a subfield of artificialintelligence, enables the identification of patterns from historical data to predict outcomes orclassifications without explicit programming [4] . This approach is believed to assist judges byaccelerating case analysis and enhancing objectivity in verdicts [5] .  \nPrior studies have demonstrated the effectiveness of ML in various legal contexts. Sohail et al.  \n[6], applied Decision Tree, K-Nearest Neighbor (KNN), and Naï","cbCainDt36dpJwEH","https://ap.wps.com/l/cbCainDt36dpJwEH","pdf",1989971,1,19,"English","en",105,"# Introduction\n## Background and problem motivation\n## Related work and research gaps\n## Research contribution and approach","[{\"question\":\"What problem does the study address in divorce verdict prediction?\",\"answer\":\"The study targets predicting divorce verdict outcomes (“Granted” or “Rejected”) in Indonesia’s Religious Courts, emphasizing the use of posita narrative text and handling severe class imbalance where one verdict class is underrepresented.\"},{\"question\":\"How is posita data processed for machine learning?\",\"answer\":\"The research applies keyword-based feature extraction to transform posita narratives into interpretable indicators that can be used by classical machine learning models.\"},{\"question\":\"Which techniques are used to handle imbalanced classes and evaluate performance?\",\"answer\":\"SMOTE is applied to the training data to mitigate class imbalance. Model performance is measured using metrics including accuracy, precision, recall, F1-score, F2-score, and AUC.\"}]","Posita Data and Imbalanced Data Handling - A Case Study | PDF",1785810365,48,{"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},"posita-data-and-imbalanced-data-handling-a-case-study","",{"@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/posita-data-and-imbalanced-data-handling-a-case-study/122388/",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","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the study address in divorce verdict prediction?","Question",{"text":75,"@type":76},"The study targets predicting divorce verdict outcomes (“Granted” or “Rejected”) in Indonesia’s Religious Courts, emphasizing the use of posita narrative text and handling severe class imbalance where one verdict class is underrepresented.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is posita data processed for machine learning?",{"text":80,"@type":76},"The research applies keyword-based feature extraction to transform posita narratives into interpretable indicators that can be used by classical machine learning models.",{"name":82,"@type":73,"acceptedAnswer":83},"Which techniques are used to handle imbalanced classes and evaluate performance?",{"text":84,"@type":76},"SMOTE is applied to the training data to mitigate class imbalance. Model performance is measured using metrics including accuracy, precision, recall, F1-score, F2-score, and AUC.","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":21,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},"General","general"]