Title:	DISCRIMINANT ANALYSIS AS A TOOL OF ASSESSING INDIVIDUAL CREDIT RISK IN POLAND’S COOPERATIVE BANKS
Author(s):	Rafa? Balina and S?awomir Juszczyk
ISBN:	978-989-8533-73-9
Editors:	Theodora Issa, Tomayess Issa, Pedro Isaias and Ana Hol
Year:	2017
Edition:	Single
Keywords:	Credit Risk, Discriminant Analysis, Cooperative Bank
Type:	Full Paper
First Page:	3
Last Page:	10
Language:	English
Cover:
Full Contents:	click to dowload
Paper Abstract:	The main objective of the study was to determine the possibility of Poland’s cooperative (co-op) banks in utilizing discriminant analysis to assess credit capability. In addition, the study also allowed the identification of opportunities for utilizing discriminant analysis for individual credit risk in determining credit capability. The addition purpose of the results was to indicate the tool enabling effective credit risk assessment by Poland’s co-op banks and identifying which profiling factors are pivotal in determining a borrower’s credit rating. In the construction of the scoring model, data from retail co-op bank clientele was used. The study assessed the discriminant function classifying potential borrowers into one of two groups i.e. the ‘good’ who should be granted said loan, and the ‘bad’ whose loan application should be rejected. From among the 28 explanatory variables describing the bank’s clients who were applying for loans, five variables found their way into the model: X1 – applicant’s age, X10 – applicant’s higher education (BS), X18 – current loan obligations, X24 – applicant’s default on loan payment, and, X25 - maximum number of days an applicant was late with due payment. These variables, coupled with assessing regressive coefficients returned a highly effective credit risk indicator identifying potentially insolvent clients. The general efficiency of the tested model on the control group was 100%, whereas for the test group 96%. What is important to note is that by taking advantage of this proposed tool, co-op banks could significantly reduce the risk associated with issuing loans to individual clients, since the model accurately identified almost all of the ‘bad’ clients. Additionally, the application of advanced statistical methods would allow a bank to avoid the risk of client insolvency and eventually protect the bank from further losses associated with debt recovery.
	Go Back