Rough sets and logistic regression analysis for loan payment

Risk classification is an important part of the financial processes. In small business loans, there is always a risk for nonpayment or non-refunding of loans though very detailed examinations are made about the company. In this study, behaviors that increase the risk in loans or causing non-refunding are tried to be determined by using the rough Set (RS) approach and logistic regression (LR). For this purpose, 121 regularly refunded and 121 irregularly refunded loans, drawn from a bank in 2006 year, were randomly selected and their attributes were examined in 2007. Examination is made in three sections for qualitative variables, for quantitative variables and for both qualitative and quantitative variables. As a result, RS model is applicable to a wide range of practical problems pertaining to loan payment prediction, but LR does not classify refund or non-refund of loan payment as good as RS, so LR can not be used for prediction. Moreover, the results show that the RS model is a promising alternative to the conventional methods for financial prediction. In fact, RS gives the attributes that affect the results negatively or positively with their measures which are used for

[1]  Sofie Balcaen,et al.  Faculteit Economie En Bedrijfskunde Hoveniersberg 24 B-9000 Gent Alternative Methodologies in Studies on Business Failure: Do They Produce Better Results than the Classical Statistical Methods? , 2022 .

[2]  Gwo-Hshiung Tzeng,et al.  Rough Set Theory in analyzing the attributes of combination values for the insurance market , 2007, Expert Syst. Appl..

[3]  Constantin Zopounidis,et al.  A survey of business failures with an emphasis on prediction methods and industrial applications , 1996 .

[4]  Francis Eng Hock Tay,et al.  Economic and financial prediction using rough sets model , 2002, Eur. J. Oper. Res..

[5]  S. Menard.  Applied Logistic Regression Analysis , 1996 .

[6]  E. Altman.  The success of business failure prediction models: An international survey , 1984 .

[7]  Zdzisław Pawlak.  A Primer on Rough Sets: A New Approach to Drawing Conclusions from Data , 2002 .

[8]  Z. Pawlak.  Rough Sets and Data Mining , 2022 .

[9]  R. C. West.  A factor-analytic approach to bank condition , 1985 .

[10]  Sancho Salcedo-Sanz,et al.  Genetic programming for the prediction of insolvency in non-life insurance companies , 2005, Comput. Oper. Res..

[11]  Malik Beshir Malik,et al.  Applied Linear Regression , 2005, Technometrics.

[12]  Gwo-Hshiung Tzeng,et al.  Rough set-based logics for multicriteria decision analysis , 2007, Eur. J. Oper. Res..

[13]  Constantin Zopounidis,et al.  Business failure prediction using rough sets , 1999, Eur. J. Oper. Res..

[14]  Anne Carroll,et al.  Using Best's Ratings in Life Insurer Insolvency Prediction , 1994 .

[15]  N. Ruzgar,et al.  Classification of the insurance sector with logistic regression , 2007 .

[16]  陳樹衡,et al.  Using Genetic Programming to Model Volatility in Financial Time Series , 1997 .

[17]  Janusz Zalewski,et al.  Rough sets: Theoretical aspects of reasoning about data , 1996 .

[18]  Andrzej Skowron,et al.  Rough sets: Some extensions , 2007, Inf. Sci..

[19]  T. Hennig-Thurau,et al.  The impact of customer satisfaction and relationship quality on customer retention: A critical reassessment and model development , 1997 .

[20]  Anurag Agarwal,et al.  Predicting Bankruptcy Resolution , 2002 .