Credit Scorecards & Forecasting Default Events – A Novel Story of Non-financial Listed Companies in Pakistan

IF 2.5 Q2 ECONOMICS
Jahanzaib Alvi, Imtiaz Arif
{"title":"Credit Scorecards & Forecasting Default Events – A Novel Story of Non-financial Listed Companies in Pakistan","authors":"Jahanzaib Alvi, Imtiaz Arif","doi":"10.1007/s10690-024-09494-3","DOIUrl":null,"url":null,"abstract":"<p>This study innovates in credit default prediction in Pakistan by developing, calibrating, and recalibrating machine learning-based credit scorecards for non-financial listed firms, leveraging extensive financial ratio analysis. This study innovates in credit default prediction in Pakistan by developing, calibrating, and recalibrating machine learning-based credit scorecards for non-financial listed firms, leveraging extensive financial ratio analysis. Identifies 12 key financial ratios out of 71 remained vital for default prediction, with Random Forest and Artificial Neural Networks leading in scorecard performance. This marks Pakistan’s first detailed scorecard approach as a potential alternative to traditional banking systems. Offers advanced risk assessment tools (credit scorecards) for improved credit risk management, aiding policymakers and finance professionals in decision-making. This research distinguishes itself through a detailed longitudinal study of non-financial Pakistani firms and a comprehensive evaluation of machine learning algorithms for default prediction. By exploiting various financial ratios to develop scorecards (an alternative of Internal Ratings-based – IRB System), it offers new insights into risk evaluation and significantly advances financial risk management. Acknowledging data limitations and variable exclusions, it sets the stage for further exploration of credit risk environment in context of Pakistan.</p>","PeriodicalId":54095,"journal":{"name":"Asia-Pacific Financial Markets","volume":"18 1","pages":""},"PeriodicalIF":2.5000,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Asia-Pacific Financial Markets","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/s10690-024-09494-3","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ECONOMICS","Score":null,"Total":0}
引用次数: 0

Abstract

This study innovates in credit default prediction in Pakistan by developing, calibrating, and recalibrating machine learning-based credit scorecards for non-financial listed firms, leveraging extensive financial ratio analysis. This study innovates in credit default prediction in Pakistan by developing, calibrating, and recalibrating machine learning-based credit scorecards for non-financial listed firms, leveraging extensive financial ratio analysis. Identifies 12 key financial ratios out of 71 remained vital for default prediction, with Random Forest and Artificial Neural Networks leading in scorecard performance. This marks Pakistan’s first detailed scorecard approach as a potential alternative to traditional banking systems. Offers advanced risk assessment tools (credit scorecards) for improved credit risk management, aiding policymakers and finance professionals in decision-making. This research distinguishes itself through a detailed longitudinal study of non-financial Pakistani firms and a comprehensive evaluation of machine learning algorithms for default prediction. By exploiting various financial ratios to develop scorecards (an alternative of Internal Ratings-based – IRB System), it offers new insights into risk evaluation and significantly advances financial risk management. Acknowledging data limitations and variable exclusions, it sets the stage for further exploration of credit risk environment in context of Pakistan.

Abstract Image

信用记分卡与违约事件预测--巴基斯坦非金融类上市公司的新故事
本研究利用广泛的财务比率分析,通过为非金融类上市公司开发、校准和重新校准基于机器学习的信用记分卡,对巴基斯坦的信用违约预测进行了创新。本研究利用广泛的财务比率分析,通过为非金融类上市公司开发、校准和重新校准基于机器学习的信用记分卡,对巴基斯坦的信用违约预测进行了创新。在 71 个仍然对违约预测至关重要的财务比率中,确定了 12 个关键比率,其中随机森林和人工神经网络在记分卡性能方面处于领先地位。这标志着巴基斯坦首次将详细的记分卡方法作为传统银行系统的潜在替代方案。提供先进的风险评估工具(信用记分卡),以改进信用风险管理,帮助政策制定者和金融专业人士做出决策。这项研究通过对巴基斯坦非金融企业进行详细的纵向研究,以及对用于违约预测的机器学习算法进行全面评估,使其与众不同。通过利用各种财务比率来开发记分卡(基于内部评级--IRB 系统的替代方法),该研究为风险评估提供了新的见解,并极大地推动了金融风险管理。在承认数据局限性和变量排除的同时,它为进一步探索巴基斯坦的信用风险环境奠定了基础。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
3.00
自引率
0.00%
发文量
34
期刊介绍: The current remarkable growth in the Asia-Pacific financial markets is certain to continue. These markets are expected to play a further important role in the world capital markets for investment and risk management. In accordance with this development, Asia-Pacific Financial Markets (formerly Financial Engineering and the Japanese Markets), the official journal of the Japanese Association of Financial Econometrics and Engineering (JAFEE), is expected to provide an international forum for researchers and practitioners in academia, industry, and government, who engage in empirical and/or theoretical research into the financial markets. We invite submission of quality papers on all aspects of finance and financial engineering. Here we interpret the term ''financial engineering'' broadly enough to cover such topics as financial time series, portfolio analysis, global asset allocation, trading strategy for investment, optimization methods, macro monetary economic analysis and pricing models for various financial assets including derivatives We stress that purely theoretical papers, as well as empirical studies that use Asia-Pacific market data, are welcome. Officially cited as: Asia-Pac Financ Markets
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信