Estimation of the Probability of Default of Consumer Credit in Ghana: Case Study of an International Bank
Loading...
Date
2011-06-20
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
This thesis uses empirical data on customer credit information to model probability of loan default in Ghana. We have constructed the logistic regression model using a dataset from an international bank in Ghana, Bank A. 9939 observations of customers were recorded of which 14% turned out to default their loan. The analyses are performed using logistic regression, with SPSS program. Six variables were found to be highly significant in the model. These are Marital Status, Number of months the applicant has been in current employment, interest rate, tenure of loan, income level and loan amount. The model was used to predict successfully the probability of default of an applicant. Applicants who are not married are 1.24 times more likely to default than those who are married. Lower income earners are more likely to default compared to higher income earners. Those who have been in their current employment for longer period are more likely to repay their loans. A unit increase in the number of months in current employment reduces the probability of default by 0.998.
Description
A thesis submitted to the School of Graduate Studies, Kwame Nkrumah University of Science and Technology, Kumasi, in partial fulfilment of the requirements for the award of the Degree of Master of Science in Industrial Mathematics