Modelling probability of default for microfinance institutions using the cox proportional hazard model

Loading...
Thumbnail Image
Date
May 20, 2019
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
In the developing countries, Small and Medium Enterprise (SMEs) has been the main engine for the needed economic growth and development. In Ghana, few work has been done on the determinants of default for microfinance institutions. The loan default by clients with its consequences within of the MFI environment in Ghana is additionally not explored. This study attempts to determine the impact of borrower characteristics on default probability changes over the life of a loan by using Survival Analysis technique. Data was acquired from the XDS Credit Bureau (authorized by the Bank of Ghana) with variables such as Time (period in months), gender of customers, amount overdue, months in arrears and age of customers. Survival Analysis was utilized to investigate the extent of covariates on default over time and to predict the probability of the default in Non-Banking Financial Institutions (Micro-finance Institutions). The cox proportional hazard regression model was used to further explain the probability of default in Non-Banking Financial Institutions in Ghana This work demonstrated that the variables amount overdue (2.537), months in arrears (4.084), age (3.542) and gender (4.016) have highly statistically significant coefficients. There is a significant distinction between the default for male and female customers, in truth showing that Females have higher risk of defaulting than their male counterparts. This subsequently leading us to conclude that Gender, Month in arrears and Amount overdue does indeed determine the chance of defaulting in Non-Banking Financial Institutions in Ghana. This study concluded that older age, higher months in arrears and higher amount overdue are associated with poorer survival (default)
Description
A thesis submitted to the Department of Mathematics, Kwame Nkrumah University of Science and Technology, in partial fulfillment of the requirement for the degree of Msc Actuarial Science,
Keywords
Modelling probability, Microfinance, Institution
Citation