Semi-Markovian credit risk modeling for consumer loans: Evidence from Kenya

Abstract

Based on simulations of implied values for credit worthiness over a period of 5 years for 1000 consumers, the study shows robustness of the Semi-Markovian models in forecasting Probabilities of Default and Loss Given Default for a portfolio of consumer loans. The study models credit risk as a reliability problem on the basis of which we generate credit risk indicators and quantify prospective capital holding based on forecast delinquencies. Consumer ratings are based on Monte-Carlo simulation techniques and the initial probability transition matrix on the Merton model. Banks could espouse the study results to fulfill regulatory credit risk capital requirements for consumer loans.