[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-291211-105":59,"doc-detail-291211-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","machine-learning-algorithms-analysis-of-synthetic-minority-oversampling-technique-smote-application-to-credit-default-prediction","Machine Learning Algorithms Analysis of Synthetic Minority Oversampling Technique (SMOTE) - Application to Credit Default Prediction","","Financial risk management relies on credit default prediction to assess borrower default risk. Class imbalance in datasets can reduce model performance, so this study evaluates how under-sampling, oversampling, and SMOTE change classifier behavior. Experiments compare multiple classifiers using a Ghanaian commercial bank dataset and evaluate AUC performance. XGBoost delivers the best AUC in most datasets, and oversampling improves minority-class prediction, supporting the value of data balancing in credit scoring.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/machine-learning-algorithms-analysis-of-synthetic-minority-oversampling-technique-smote-application-to-credit-default-prediction/291211/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/machine-learning-algorithms-analysis-of-synthetic-minority-oversampling-technique-smote-application-to-credit-default-prediction/291211.png","ImageObject",300,407,{"name":92,"@type":93},"Valentina","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-11","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",14,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"Why is credit default prediction affected by class imbalance?","Question",{"text":113,"@type":114},"Imbalanced datasets contain far fewer default (minority) cases than non-default (majority) cases. Standard classifiers then favor the majority distribution, leading to weaker prediction of minority-class events.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"What imbalance techniques does the study compare?",{"text":118,"@type":114},"The study examines under-sampling, over-sampling, and SMOTE, analyzing how each resampling approach affects classifier performance on the credit default task.",{"name":120,"@type":111,"acceptedAnswer":121},"Which classifier performed best according to the abstract?",{"text":122,"@type":114},"The abstract reports that XGBoost outperformed other classifiers in AUC across most datasets, with an exception related to SMOTE performance on the Ghanaian commercial bank dataset.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},291211,1789643749,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":145,"preview_page_count":4},13056703020460,"https://ap-avatar.wpscdn.com/avatar/be000253dac470eee5d?_k=1778207105932848923","Ratio Mathematica Volume 53, 2024  \nMachine Learning Algorithms Analysis of Synthetic Minority Oversampling Technique (SMOTE): Application to Credit  \nDefault Prediction  \nEmmanuel de-Graft Johnson Owusu-Ansah􀀃  \nRichard Doamekpory Richard Kodzo Avuglahz Yaa Adwubi Kyerex  \nAbstract  \nFinancial risk management requires credit default prediction to measure borrower default risk. Class Imbalance in datasets can hinder model performance. This study examines how under-sampling, oversampling, and SMOTE affect classifier performance. XGBoost outperformed other classifiers in AUC across most datasets except SMOTE using a Ghanaian commercial bank dataset.It concludes that oversampling outperforms under-sampling in enhancing classifier performance and improving the prediction of minority class occurrences, demonstrating the value of data balancing in credit scoring models.  \nKeywords: SMOTE; Class Imbalanced; Machine Learning; Resampling; Credit Worthiness  \n2020 AMS subject classifications: 6208, 6211, 62D99 1  \n􀀃 Statistics and Actuarial Sci., Kwame Nkrumah University of Science & Technology, Ghana; [edjowusu-ansah.cos@knust.edu.gh](edjowusu-ansah.cos@knust.edu.gh)  \ny Statistics and Actuarial Sci., Kwame Nkrumah Univ. of Sci. & Tech. ;[mylordc2@gmail.com](mylordc2@gmail.com)[ ](mylordc2@gmail.com)z Statistics and Actuarial Sci., Kwame Nkrumah Univ. of Sci. & Tech. ; [avuglah@gmail.com](avuglah@gmail.com)[ ](avuglah@gmail.com)x Statistics and Actuarial Sci., Kwame Nkrumah Univ. of Sci. & Tech. ; [avuglah@gmail.com](avuglah@gmail.com)  \n[1](1 Received on May 12)[ Received on May 12](1 Received on May 12), [2024](2024). Accepted on December 5, 2024 . Published on December 31, 2024 . DOI:10.23755/rm.v53i0.1601 . ISSN: 1592-7415 . eISSN: 2282-8214 . 􀀍c Owusu-Ansah et al. This paper is published under the CC-BY licence agreement.  \nEmmanuel de-Graft Johnson Owusu-Ansah, Richard Doamekpor, Richard Kodzo  \nAvuglah, YaaAdwubi Kyere  \n1 Introduction  \nImbalanced learning is one of the most challenging tasks in data mining. In imbalance learning, some classes have inadequate data while others have an abundance of data. Imbalanced data sets are often encountered in ”anomaly-type”classification problems. These issues are divided into two categories: ”normal”and ”anomaly,” with ”anomaly” including a broad variety of meanings. Examples include medical diagnosis Chan P [1999], machine failure detection Rao R, and fraud detection Kerdprasop K [2011] .  \nWhen trying to foresee occurrences, it is critical to concentrate on the minority class since it varies from the majority class's typical trends. Standard classifiers are designed to decrease overall classification errors, regardless of class distribution. As a consequence, these classifiers emphasize majority-class samples above minority-class accuracy. There are three fundamental strategies for correcting data imbalance: cost-sensitive, algorithm-level, and data-level. The cost-sensitive approach calculates misclassification costs using class relevance and imbalance. Examples of cost-sensitive techniques are AdaCost [Fan W,] and the work in [Sun Y, 2007] . The data level approach entails changing the data to re-balance minority and majority categories. To do this, either under-sample the majority class or over-sample the minority class. The imbalance technique is extensively used due of its simplicity and universality, which make it usable regardless of classifier type. Behind the sample overlay, the classifier is intact. Under-sampling (Figure1) is the process of removing less significant patterns using random or heuristic criteria. Examples of under-sampling include the condensed nearest neighbor rule [Batista G E, 2004,] and one-sided selection [Fayed H, 2009] .  \nFigure 1: Undersampling and Oversampling of an Imbalance data Source: [Roweida M, 2020]  \nHowever, under-sampling is risky since critical information may be overlooked. Over-sampling [Fayed H, 2009] is most likely a more successful method. Minorit","cbCaigTKHTQzoIRl","https://ap.wps.com/l/cbCaigTKHTQzoIRl","pdf",313790,27,"English","# Abstract\n# Introduction\n## Class imbalance and its impact\n## Strategies to correct imbalance (cost-, algorithm-, data-level)\n## Under-sampling and over-sampling\n## Ensemble methods with resampling","[{\"question\":\"Why is credit default prediction affected by class imbalance?\",\"answer\":\"Imbalanced datasets contain far fewer default (minority) cases than non-default (majority) cases. Standard classifiers then favor the majority distribution, leading to weaker prediction of minority-class events.\"},{\"question\":\"What imbalance techniques does the study compare?\",\"answer\":\"The study examines under-sampling, over-sampling, and SMOTE, analyzing how each resampling approach affects classifier performance on the credit default task.\"},{\"question\":\"Which classifier performed best according to the abstract?\",\"answer\":\"The abstract reports that XGBoost outperformed other classifiers in AUC across most datasets, with an exception related to SMOTE performance on the Ghanaian commercial bank dataset.\"}]","Machine Learning Algorithms Analysis of Synthetic Minority Oversampling Technique (SMOTE) - Application to Credit Default Prediction | PDF",68]