[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121160-en":3,"doc-seo-121160-105":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},121160,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Credit Default Prediction Model Using Machine Learning for Credit Monitoring - Empirical Study on Banking in Indonesia","Credit default represents a borrower’s failure to meet required principal or interest repayments, creating significant exposure within credit risk management. This study applies machine learning to credit monitoring by predicting default for working capital credit and investment credit using non-demographic debtor data, then evaluates accuracy, precision, and variable importance. The dataset covers monthly credit records from 105 Indonesian banks from August 2018 to December 2019. Results indicate market-price related variables and credit interest rates affect default, while credit tenor does not consistently support the tested hypothesis.","Credit Default Prediction Model Using Machine Learning for Credit Monitoring: Empirical Study on Banking in  \nIndonesia  \nAndri Ismatullah Gani 1 , Irene Rini Demi Pangestuti 2  \nAbstract:  \nCredit default is the failure of a borrower to make required principal or interest repayments on a debt. In credit risk management, it is important for banks to anticipate credit defaults, whether in the credit underwriting process or in the area of credit monitoring. In this study we focus on the use of machine learning in the area of credit monitoring to predict default of working capital credit and investment credit based on non-demographic debtors’ data, where we then test model’s accuracy and level of precision that can be achieved, and identify variables that have high importance on the predictive model. The population of this research is all detailed credit data provided by all banks in Indonesia for the monthly period from August 2018 to December 2019 (17 months) consisting of a total of 517,516,584. The research sample is credit provided by banks based on type of use, namely for consumption, working capital or investment, after special filtering for credit account data from 105 banks in Indonesia for the period August 2018 to December 2019. Analysis techniques build predictive models to analyze potential default facilities credit, using traditional statistical models which are parmetric models and comparing them with non-parametric models using Artificial Intelligence / Machine Learning. The research results have not been proven based on the ML algorithm that debtor ranking has no effect on default (H1 is rejected). Percentage Change in Market Prices has a negative relationship with credit default which is proven based on the results of the ML model produced (H2 is accepted). Market Price Period has a positive relationship with credit default, which is proven based on the results of the ML model (H3 is accepted). This shows that credit interest rates have an effect on credit default in the ML model (H4 is accepted). Credit Tenor has a negative relationship with credit default in the ML model (H5 is rejected).  \nKeywords : Machine Learning, Explainable Artificial Intelligence, Predictive Model, Classification, Credit Default  \nSubmitted: 21 January 2024, Accepted: 12 March 2024, Published: 31 August 2024  \n1. Introduction  \nBanks are financial intermediaries that accept deposits from the public and provide credit products for borrowers. The Basel Committee on Banking Supervision (BCBS) as the primary global standard-setter for the prudential regulation of banks has identified the following key banking risks: (i) credit,(ii) market,(iii) operational,(iv) liquidity, and (v) systemic, as set out in Basel III (BCBS, 2015) . Credit risk arises when a bank lends money to a borrower, because there is a probability that the  \n1Master of Management, Universitas Diponegoro, Indonesia, [andrigani@outlook.com](andrigani@outlook.com)[ ](andrigani@outlook.com)2Master of Management, Universitas Diponegoro, Indonesia, [irenerinidp1960@gmail.com](irenerinidp1960@gmail.com)  \nborrower fails to repay the debt and the bank lose money (Barakat & Hussainey, 2013) . According to Buehler et al. (2008), about 60% of bank’s threat is represented by credit risk. Therefore, having effective credit risk management is crucial for banks to minimize losses, protect customer trust, and ensure compliance with relevant regulations.  \nCredit default is a credit risk where a borrower fails to make required principal or interest repayments on a debt. Depending on a number of factors, borrower default may cause great loss to a bank, therefore it is important for banks to be able to anticipate the likelihood that a borrower will default. In general, this can be conducted during the credit underwriting process, which is the process of evaluating the creditworthiness and repayment ability of potential borrower for new credit applications, or during the credit monitoring pr","cbCaioKoXqFLrEx3","https://ap.wps.com/l/cbCaioKoXqFLrEx3","pdf",439917,1,15,"English","en",105,"# Introduction\n## Credit risk and credit default\n## Motivation for machine learning in credit monitoring\n## Research objectives and approach","[{\"question\":\"What is the main objective of the study?\",\"answer\":\"To build and evaluate machine learning models for predicting credit default in existing credit portfolios, specifically working capital credit and investment credit, and to identify important predictive variables.\"},{\"question\":\"Which data period and banking scope are used for model development?\",\"answer\":\"Monthly snapshots of credit accounts from 105 banks in Indonesia covering August 2018 to December 2019 are used to construct the predictive models.\"},{\"question\":\"Which factors show evidence of relationships with credit default in the ML results?\",\"answer\":\"Percentage change in market prices has a negative relationship with credit default, while market price period shows a positive relationship; credit interest rates are also found to affect credit default in the ML model.\"}]","Credit Default Prediction Model Using Machine Learning for Credit Monitoring - Empirical Study on Banking in Indonesia | PDF",1785734141,38,{"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},"credit-default-prediction-model-using-machine-learning-for-credit-monitoring-empirical-study-on-banking-in-indonesia","",{"@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/credit-default-prediction-model-using-machine-learning-for-credit-monitoring-empirical-study-on-banking-in-indonesia/121160/",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":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main objective of the study?","Question",{"text":75,"@type":76},"To build and evaluate machine learning models for predicting credit default in existing credit portfolios, specifically working capital credit and investment credit, and to identify important predictive variables.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which data period and banking scope are used for model development?",{"text":80,"@type":76},"Monthly snapshots of credit accounts from 105 banks in Indonesia covering August 2018 to December 2019 are used to construct the predictive models.",{"name":82,"@type":73,"acceptedAnswer":83},"Which factors show evidence of relationships with credit default in the ML results?",{"text":84,"@type":76},"Percentage change in market prices has a negative relationship with credit default, while market price period shows a positive relationship; credit interest rates are also found to affect credit default in the ML model.","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"]