Improving retail banking loans recovery via data mining techniques: a case study from Indian market

Q2 Business, Management and Accounting

International Journal of Electronic Customer Relationship Management Pub Date : 2016-01-06 DOI:10.1504/ijecrm.2015.071716

V. Ravi, Sagar Koparkar, N. Raju, S. Sridher

{"title":"Improving retail banking loans recovery via data mining techniques: a case study from Indian market","authors":"V. Ravi, Sagar Koparkar, N. Raju, S. Sridher","doi":"10.1504/ijecrm.2015.071716","DOIUrl":null,"url":null,"abstract":"In 2006-2007, the Indian banks saw a phenomenal increase in their loans, because of global growth, and mortgage market in the USA. But this was a 'bubble', hence did not sustain. Then global recession set in affecting the financial market in India. The default rates on unsecured borrowing rose and recovery became difficult. Banks spent more resources for their recovery. But in the process, borrower information was ignored, although credit bureau information about the borrower was available. This paper demonstrates that data mining techniques can find out defaulters who are most likely to pay, hence focusing recovery efforts on them. We tested the predictive power of neural network (NN), CART (DT) and logistic regression (LR) on the data of one of the bank's personal loan portfolio. Also, we demonstrated the use of 'textual data' available in the form of interaction with the borrowers and its value addition in predicting their payment behaviour.","PeriodicalId":39480,"journal":{"name":"International Journal of Electronic Customer Relationship Management","volume":"1 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2016-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1504/ijecrm.2015.071716","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Electronic Customer Relationship Management","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1504/ijecrm.2015.071716","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"Business, Management and Accounting","Score":null,"Total":0}

引用次数: 2

Abstract

In 2006-2007, the Indian banks saw a phenomenal increase in their loans, because of global growth, and mortgage market in the USA. But this was a 'bubble', hence did not sustain. Then global recession set in affecting the financial market in India. The default rates on unsecured borrowing rose and recovery became difficult. Banks spent more resources for their recovery. But in the process, borrower information was ignored, although credit bureau information about the borrower was available. This paper demonstrates that data mining techniques can find out defaulters who are most likely to pay, hence focusing recovery efforts on them. We tested the predictive power of neural network (NN), CART (DT) and logistic regression (LR) on the data of one of the bank's personal loan portfolio. Also, we demonstrated the use of 'textual data' available in the form of interaction with the borrowers and its value addition in predicting their payment behaviour.

查看原文本刊更多论文

通过数据挖掘技术改善零售银行贷款回收:来自印度市场的案例研究

2006-2007年，由于全球经济增长和美国抵押贷款市场，印度银行的贷款出现了惊人的增长。但这是一个“泡沫”，因此没有持续下去。随后，全球经济衰退开始影响印度的金融市场。无担保借款的违约率上升，复苏变得困难。银行为复苏投入了更多资源。但是在这个过程中，借款人的信息被忽略了，尽管有关借款人的征信机构的信息是可用的。本文证明了数据挖掘技术可以找出最有可能付款的违约者，从而将恢复工作集中在他们身上。我们测试了神经网络(NN)、CART (DT)和逻辑回归(LR)对某银行个人贷款组合数据的预测能力。此外，我们展示了与借款人互动形式的“文本数据”的使用及其在预测其支付行为方面的附加价值。

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

International Journal of Electronic Customer Relationship Management Business, Management and Accounting-Business, Management and Accounting (all)

CiteScore

1.30

自引率

0.00%

发文量

期刊介绍： The aim of IJECRM is to provide an international forum and refereed reference in the field of electronic customer relationship management (ECRM). It also addresses the interaction, collaboration, partnership and cooperation between small and medium sized enterprises (SMEs) and larger enterprises in a customer relationship. More innovative analysis and better understanding of the complexity involved in a customer relationship are essential in today''s global businesses. Therefore, manuscripts offering theoretical, conceptual, and practical contributions for ECRM are encouraged. Topics covered include: -Electronic customer relationship management (ECRM) -CRM strategy, marketing, technology and software -Custom marketing and sales management -Customer lifetime value, loyalty, satisfaction, behaviour, databases -Issues for implementing CRM systems/solutions for CRM problems -Tools for capturing customer information, managing/sharing customer data -Partner relationship management, strategic alliances/ partnerships -Business to business market (B2B), business to consumer market (B2C) -Enterprise resource planning (ERP) -Supply chain dynamics and uncertainty, supplier relationship management (SRM) -E-commerce customer relationships on the internet -Supply chain management, channel management, demand chain management -Manufacturing, logistics and information technology/systems -Supplier and distribution networks, international issues -Performance measurement/indicators, research, modelling