{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T01:09:32Z","timestamp":1776128972858,"version":"3.50.1"},"reference-count":53,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2023,10,5]],"date-time":"2023-10-05T00:00:00Z","timestamp":1696464000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Systems"],"abstract":"<jats:p>The loss given default (LGD) is an important credit risk parameter in the regulatory system for financial institutions. Due to the complex structure of the LGD distribution, we propose a new approach, called the hybrid algorithms multi-stage (HMS) model, to construct a multi-stage LGD prediction model and test it on the US Small Business Administration (SBA)\u2019s small business credit dataset. We then compare the model\u2019s performance under four routes by different evaluation metrics. Finally, pertinent business information and macroeconomic features datasets are added for robustness validation. The results show that HMS performs well and stably for predicting LGD, confirming the superiority of the proposed hybrid unsupervised and supervised machine learning algorithm. Financial institutions can apply the approach to make default predictions based on other credit datasets.<\/jats:p>","DOI":"10.3390\/systems11100505","type":"journal-article","created":{"date-parts":[[2023,10,5]],"date-time":"2023-10-05T09:14:22Z","timestamp":1696497262000},"page":"505","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Assessing the Loss Given Default of Bank Loans Using the Hybrid Algorithms Multi-Stage Model"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2651-4520","authenticated-orcid":false,"given":"Mengting","family":"Fan","sequence":"first","affiliation":[{"name":"School of Management, Guangdong University of Technology, Guangzhou 510520, China"}]},{"given":"Tsung-Hsien","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Management, Fu Jen Catholic University, New Taipei City 242062, Taiwan"}]},{"given":"Qizhi","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Management, Guangdong University of Technology, Guangzhou 510520, China"}]}],"member":"1968","published-online":{"date-parts":[[2023,10,5]]},"reference":[{"key":"ref_1","first-page":"117","article-title":"Classification methods applied to credit scoring: Systematic review and overall comparison","volume":"21","author":"Louzada","year":"2016","journal-title":"Surv. Oper. Res. Manag. Sci."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"116889","DOI":"10.1016\/j.eswa.2022.116889","article-title":"Assessing credit risk of commercial customers using hybrid machine learning algorithms","volume":"200","author":"Machado","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1007\/s11518-009-5109-y","article-title":"Combining classifiers for credit risk prediction","volume":"18","author":"Twala","year":"2009","journal-title":"J. Syst. Sci. Syst. Eng."},{"key":"ref_4","unstructured":"Basel Committee on Banking Supervision (2003). Overview of The New Basel Capital Accord, Bank for International Settlements."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2354","DOI":"10.1016\/j.jbankfin.2013.01.031","article-title":"Improvements in loss given default forecasts for bank loans","volume":"37","author":"Hibbeln","year":"2013","journal-title":"J. Bank. Financ."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/j.ijforecast.2010.08.005","article-title":"Loss given default models incorporating macroeconomic variables for credit cards","volume":"28","author":"Bellotti","year":"2012","journal-title":"Int. J. Forecast."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"116295","DOI":"10.1016\/j.eswa.2021.116295","article-title":"Modelling spatial dependence for Loss Given Default in peer-to-peer lending","volume":"192","author":"Calabrese","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/j.dss.2016.06.014","article-title":"The use of profit scoring as an alternative to credit scoring systems in peer-to-peer (P2P) lending","volume":"89","year":"2016","journal-title":"Decis. Support Syst."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1016\/j.ijforecast.2010.06.002","article-title":"Comparisons of linear regression and survival analysis using single and mixture distributions approaches in modelling LGD","volume":"28","author":"Zhang","year":"2012","journal-title":"Int. J. Forecast."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"106334","DOI":"10.1016\/j.jbankfin.2021.106334","article-title":"Opening the black box\u2013Quantile neural networks for loss given default prediction","volume":"134","author":"Kellner","year":"2022","journal-title":"J. Bank. Financ."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/j.ijforecast.2011.01.006","article-title":"Benchmarking regression algorithms for loss given default modeling","volume":"28","author":"Loterman","year":"2012","journal-title":"Int. J. Forecast."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"107068","DOI":"10.1016\/j.knosys.2021.107068","article-title":"Predicting loss given default using post-default information","volume":"224","author":"Li","year":"2021","journal-title":"Knowl.-Based Syst."},{"key":"ref_13","unstructured":"Lucas, A. (2006). Basel II Problem Solving, QFRMC Workshop and Conference on Basel II & Credit Risk Modelling in Consumer Lending, University of Southampton."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1016\/j.ijforecast.2016.11.005","article-title":"Forecasting loss given default of bank loans with multi-stage model","volume":"33","author":"Tanoue","year":"2017","journal-title":"Int. J. Forecast."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1016\/j.eswa.2019.02.033","article-title":"Integration of unsupervised and supervised machine learning algorithms for credit risk assessment","volume":"128","author":"Bao","year":"2019","journal-title":"Expert Syst. Appl."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1080\/10691898.2018.1434342","article-title":"\u201cShould This Loan be Approved or Denied?\u201d: A Large Dataset with Class Assignment Guidelines","volume":"26","author":"Li","year":"2018","journal-title":"J. Stat. Educ."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1016\/j.econmod.2019.11.032","article-title":"Exploring the mismatch between credit ratings and loss-given-default: A credit risk approach","volume":"85","author":"Shi","year":"2020","journal-title":"Econ. Model."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1016\/j.frl.2019.03.033","article-title":"Credit rating and microfinance lending decisions based on loss given default (LGD)","volume":"30","author":"Shi","year":"2019","journal-title":"Financ. Res. Lett."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.jbankfin.2011.06.005","article-title":"Credit rating dynamics in the presence of unknown structural breaks","volume":"36","author":"Xing","year":"2012","journal-title":"J. Bank. Financ."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2433","DOI":"10.1016\/j.eswa.2011.08.093","article-title":"Does segmentation always improve model performance in credit scoring?","volume":"39","author":"Bijak","year":"2012","journal-title":"Expert Syst. Appl."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1269","DOI":"10.1016\/j.jbankfin.2007.10.012","article-title":"The delivery option in credit default swaps","volume":"32","author":"Jankowitsch","year":"2008","journal-title":"J. Bank. Financ."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"903","DOI":"10.1016\/j.jbankfin.2009.10.001","article-title":"Bank loan recovery rates: Measuring and nonparametric density estimation","volume":"34","author":"Calabrese","year":"2010","journal-title":"J. Bank. Financ."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2915","DOI":"10.1016\/j.jbankfin.2003.10.018","article-title":"On the way to recovery: A nonparametric bias free estimation of recovery rate densities","volume":"28","author":"Renault","year":"2004","journal-title":"J. Bank. Financ."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1016\/j.jfineco.2006.05.011","article-title":"Does industry-wide distress affect defaulted firms? Evidence from creditor recoveries","volume":"85","author":"Acharya","year":"2007","journal-title":"J. Financ. Econ."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2203","DOI":"10.1086\/497044","article-title":"The link between default and recovery rates: Theory, empirical evidence, and implications","volume":"78","author":"Altman","year":"2005","journal-title":"J. Bus."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1111\/j.1468-036X.2010.00582.x","article-title":"Default and recovery risk dependencies in a simple credit risk model","volume":"17","author":"Bade","year":"2011","journal-title":"Eur. Financ. Manag."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"619","DOI":"10.1002\/(SICI)1099-1255(199611)11:6<619::AID-JAE418>3.0.CO;2-1","article-title":"Econometric methods for fractional response variables with an application to 401 (k) plan participation rates","volume":"11","author":"Papke","year":"1996","journal-title":"J. Appl. Econom."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1016\/j.eswa.2017.04.006","article-title":"Machine learning models and bankruptcy prediction","volume":"83","author":"Barboza","year":"2017","journal-title":"Expert Syst. Appl."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2510","DOI":"10.1016\/j.jbankfin.2010.04.011","article-title":"Forecasting bank loans loss-given-default","volume":"34","author":"Bastos","year":"2010","journal-title":"J. Bank. Financ."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"113567","DOI":"10.1016\/j.eswa.2020.113567","article-title":"Corporate default forecasting with machine learning","volume":"161","author":"Moscatelli","year":"2020","journal-title":"Expert Syst. Appl."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"528","DOI":"10.1016\/j.ejor.2014.06.043","article-title":"Support vector regression for loss given default modelling","volume":"240","author":"Yao","year":"2015","journal-title":"Eur. J. Oper. Res."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"428","DOI":"10.1016\/j.ijforecast.2020.06.009","article-title":"Forecasting recovery rates on non-performing loans with machine learning","volume":"37","author":"Bellotti","year":"2021","journal-title":"Int. J. Forecast."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1016\/j.ejor.2018.01.020","article-title":"Loss functions for loss given default model comparison","volume":"268","author":"Hurlin","year":"2018","journal-title":"Eur. J. Oper. Res."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1016\/j.ijforecast.2019.05.009","article-title":"Predicting loss given default in leasing: A closer look at models and variable selection","volume":"36","author":"Kaposty","year":"2020","journal-title":"Int. J. Forecast."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/j.jbankfin.2017.01.020","article-title":"Loss given default adjusted workout processes for leases","volume":"91","author":"Miller","year":"2018","journal-title":"J. Bank. Financ."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"97","DOI":"10.22436\/jmcs.06.02.02","article-title":"A new method for clustering in credit scoring problems","volume":"6","author":"Gholamian","year":"2013","journal-title":"J. Math. Comput. Sci."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"7562","DOI":"10.1016\/j.eswa.2008.09.028","article-title":"Prediction model building with clustering-launched classification and support vector machines in credit scoring","volume":"36","author":"Luo","year":"2009","journal-title":"Expert Syst. Appl."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1351","DOI":"10.1016\/j.eswa.2009.06.083","article-title":"Support vector machine based multiagent ensemble learning for credit risk evaluation","volume":"37","author":"Yu","year":"2010","journal-title":"Expert Syst. Appl."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1016\/j.ijpe.2016.04.012","article-title":"Corporate credit-risk evaluation system: Integrating explicit and implicit financial performances","volume":"177","author":"Zhang","year":"2016","journal-title":"Int. J. Prod. Econ."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1329","DOI":"10.1007\/s00521-016-2567-2","article-title":"Improve credit scoring using transfer of learned knowledge from self-organizing map","volume":"28","author":"AghaeiRad","year":"2017","journal-title":"Neural Comput. Appl."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1016\/j.eswa.2005.10.005","article-title":"Failure prediction with self organizing maps","volume":"30","author":"Huysmans","year":"2006","journal-title":"Expert Syst. Appl."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/j.dss.2019.01.002","article-title":"Two-stage consumer credit risk modelling using heterogeneous ensemble learning","volume":"118","author":"Papouskova","year":"2019","journal-title":"Decis. Support Syst."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"100850","DOI":"10.1016\/j.seps.2020.100850","article-title":"Cluster Analysis for mixed data: An application to credit risk evaluation","volume":"73","author":"Caruso","year":"2021","journal-title":"Socio-Econ. Plan. Sci."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1464","DOI":"10.1109\/5.58325","article-title":"The self-organizing map","volume":"78","author":"Kohonen","year":"1990","journal-title":"Proc. IEEE"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1080\/01605682.2020.1865847","article-title":"Machine learning methods for short-term probability of default: A comparison of classification, regression and ranking methods","volume":"73","author":"Coenen","year":"2022","journal-title":"J. Oper. Res. Soc."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"2842","DOI":"10.1016\/j.jbankfin.2011.03.011","article-title":"Comparison of modeling methods for loss given default","volume":"35","author":"Qi","year":"2011","journal-title":"J. Bank. Financ."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Munkhdalai, L., Munkhdalai, T., Namsrai, O.-E., Lee, J.Y., and Ryu, K.H. (2019). An empirical comparison of machine-learning methods on bank client credit assessments. Sustainability, 11.","DOI":"10.3390\/su11030699"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"1590","DOI":"10.1016\/j.ijforecast.2021.03.002","article-title":"Forecasting loss given default for peer-to-peer loans via heterogeneous stacking ensemble approach","volume":"37","author":"Xia","year":"2021","journal-title":"Int. J. Forecast."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1016\/j.jempfin.2021.08.009","article-title":"Machine learning loss given default for corporate debt","volume":"64","author":"Olson","year":"2021","journal-title":"J. Empir. Financ."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"de Lange, P.E., Melsom, B., Venner\u00f8d, C.B., and Westgaard, S. (2022). Explainable AI for Credit Assessment in Banks. J. Risk Financ. Manag., 15.","DOI":"10.3390\/jrfm15120556"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"113986","DOI":"10.1016\/j.eswa.2020.113986","article-title":"A benchmark of machine learning approaches for credit score prediction","volume":"165","author":"Moscato","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"108105","DOI":"10.1016\/j.ymssp.2021.108105","article-title":"An explainable artificial intelligence approach for unsupervised fault detection and diagnosis in rotating machinery","volume":"163","author":"Brito","year":"2022","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_53","unstructured":"Gupton, G.M., Stein, R.M., Salaam, A., and Bren, D. (2002). LossCalcTM: Model for Predicting Loss Given Default (LGD), Moody\u2019s KMV."}],"container-title":["Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-8954\/11\/10\/505\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:01:33Z","timestamp":1760130093000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-8954\/11\/10\/505"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,5]]},"references-count":53,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2023,10]]}},"alternative-id":["systems11100505"],"URL":"https:\/\/doi.org\/10.3390\/systems11100505","relation":{},"ISSN":["2079-8954"],"issn-type":[{"value":"2079-8954","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,5]]}}}