[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118162-en":3,"doc-seo-118162-105":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},118162,8796095462418,"Noah","https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780",8,"Research & Report","DISCRIMINATIVE ABILITY IN ESTIMATING PROBABILITY OF DEFAULT WITH CERTAIN MACHINE LEARNING ALGORITHMS","The research presents machine learning as a value-adding approach for estimating the probability of default in credit risk management. It examines how discriminative ability changes when specific algorithms are applied to the analyzed sample and compares results against traditionally established models. Findings show that machine learning delivers superior discriminative performance, supporting more precise risk evaluation. For business organizations exposed to credit risk, improved default prediction can help reduce credit losses, especially across larger transaction volumes.","DISCRIMINATIVE ABILITY  \nIN ESTIMATING PROBABILITY  \nOF DEFAULT WITH CERTAIN MACHINE LEARNING ALGORITHMS  \nAntonio V. Dichev1  \n1D. A. Tsenov Academy of Economics – Svishtov, Bulgaria [E-mail:](E-mail:1 antoniodichev@yahoo.com)[1](E-mail:1 antoniodichev@yahoo.com)[ antoniodichev@yahoo.com](E-mail:1 antoniodichev@yahoo.com)  \nAbstract: The article highlights the importance and added value ofsome machine learning algorithms in assessing default probability. The results of the research highlight the discriminative ability added to many other essential aspects of machine learning in assessing credit risk. These aspects can be identified as specific opportunities and challenges. As for the discriminative ability regarding the analysed sample, the results prove the superiority of machine learning over the traditionally established and known models. For individual business organizations with exposures to credit risk, machine learning could contribute to reducing the credit losses with larger volumes of business transactions.  \nKeywords: probability of default, machine learning, risk assessment, credit risk.  \nThis article shall be cited as follows: Dichev, А. (2023) . Discriminative Ability in Estimating Probability of Default with Certain Machine Learning Algorithms. Economic Archive,(4), pp. 16-27.  \n[URL:](URL: nsarhiv.uni-svishtov.bg)[ nsarhiv.uni-svishtov.bg](URL: nsarhiv.uni-svishtov.bg)  \nDOI: [https://doi.org/10.58861/tae.ea-nsa.2023.4.02.en](https://doi.org/10.58861/tae.ea-nsa.2023.4.02.en)  \n[JEL:](JEL:) В23, C58, G32 .  \n* * *  \nHistorically, well-configured risk management and assessment frame  \nworks have proven their key role in the sector of finance. The use of precise models that encompass the largest possible number of factors and volumes of information is a key factor for achieving an objective risk management framework with minimal number of elements of subjectivity. In  \n16 Economic Archive 4/2023  \nthe digital age, machine learning plays an essential role in analyses of large datasets where the detection of more difficult-to-observe dependencies and the construction of risk models with a markedly high accuracy.  \nIn this regard, the subject of the research presented in this article is machine learning. The research object is the assessment of the probability of default (PD) . The research thesis is formulated as follows: By applying machine learning methods to the assessment of the probability of default, additional precision can be achieved.  \nThe aim of the research is to approbate machine learning as a valueadding tool in credit risk management. The main research task is to determine the effect of some machine learning algorithms on the discriminative ability in estimating the probability of default.  \n1. Theoretical foundations and a review of publications on the topic  \n1.1. General definition of machine learning (ML)  \nMany of the available literary source refer to the following definition of machine learning (ML):  \n“A computer program is said to learn from experience E with respect to some class of tasks Tand performance measure P, if its performance at tasks in T, as measured by P, improves with experience E.”(Mitchell, 1997, p. 2) .  \nAlthough logistic regression fits the above definition and theoretically falls within the scope of machine learning, in this research it is considered an alternative to machine learning algorithms, i.e. it is seen as a representative of the already established traditional algorithms and methods for modelling the probability of default (PD) . This distinction was made because, in practice, logistic regression is often not recognized and regarded as an ML algorithm. The above distinction assumed by the author is also suggested by the current regulatory and institutional discussions in the banking sector (EBA, 2021) .  \n1.2. Probability of default as an element of credit risk  \nAccording to the Basel Committee on Banking Supervision (BCBS, 2000), credit risk is the potential ","cbCaitsxF3onaLdf","https://ap.wps.com/l/cbCaitsxF3onaLdf","pdf",1554338,1,15,"English","en",105,"# Abstract\n# Research Focus and Thesis\n## Research Aim and Task\n# Theoretical Foundations and Literature Review\n## General Definition of Machine Learning (ML)\n## Probability of Default as an Element of Credit Risk","[{\"question\":\"What is the main research objective of the article?\",\"answer\":\"The article aims to validate machine learning as a value-adding tool in credit risk management. It focuses on determining the effect of certain algorithms on the discriminative ability for estimating probability of default.\"},{\"question\":\"How does the paper define probability of default (PD) in the credit risk context?\",\"answer\":\"PD is treated as a key measure representing the likelihood that a borrower will be unable to meet debt obligations over a specific time horizon. It is used for internal decision-making and regulatory capital determination.\"},{\"question\":\"What do the results indicate about machine learning versus traditional models?\",\"answer\":\"For the analyzed sample, the results demonstrate the superiority of machine learning in discriminative ability compared with traditionally established models. This suggests more accurate probability-of-default estimation.\"}]","DISCRIMINATIVE ABILITY IN ESTIMATING PROBABILITY OF DEFAULT WITH CERTAIN MACHINE LEARNING ALGORITHMS | PDF",1785681949,38,{"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},"discriminative-ability-in-estimating-probability-of-default-with-certain-machine-learning-algorithms","",{"@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/discriminative-ability-in-estimating-probability-of-default-with-certain-machine-learning-algorithms/118162/",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","2026-08-02",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 is the main research objective of the article?","Question",{"text":75,"@type":76},"The article aims to validate machine learning as a value-adding tool in credit risk management. It focuses on determining the effect of certain algorithms on the discriminative ability for estimating probability of default.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the paper define probability of default (PD) in the credit risk context?",{"text":80,"@type":76},"PD is treated as a key measure representing the likelihood that a borrower will be unable to meet debt obligations over a specific time horizon. It is used for internal decision-making and regulatory capital determination.",{"name":82,"@type":73,"acceptedAnswer":83},"What do the results indicate about machine learning versus traditional models?",{"text":84,"@type":76},"For the analyzed sample, the results demonstrate the superiority of machine learning in discriminative ability compared with traditionally established models. This suggests more accurate probability-of-default estimation.","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"]