Credit risk modelling by commercial banks in Southern Africa in the presence of market friction (1997 - 2020)

Abstract

The research proposes and examines new structural equity, risk of default, expected loss, and profitability models for banks in frictional and fuzzy financial markets. It is motivated by the need to fill the shortcomings of structural probability-based asset and credit risk models such as Merton (1974) and Black and Scholes (1973) that are characterised by unrealistic assumptions such as crisply precise and constant risk-free rates of return and asset volatilities. The problem investigated here specifically proposes new Kealhofer-Merton-Vasicek (KMV) and vector auto-regression (VAR) models for the valuation of equities, risks of default, expected losses, and profitability of banks respectively which are extended for both market friction represented by transaction costs and uncertainty modelled by fuzziness. The respective novel valuation models are then validated using cross-sectional financial data of listed banking corporations drawn from several emerging economies in Southern Africa. The results from the proposed equity and credit risk models are fairly stable, reliable, and consistent compared to those from conventional or structural credit risk models currently used for bank valuations in the markets. Therefore these proposed models are relevant in that they fairly capture practical conditions faced by banks in emerging markets that influence their equity, risk metrics, and credit exposures in their quest to improve capitalisation, financial performance, and shareholders' wealth. The study recommends that banks in frictional and fuzzy financial markets, such as those in emerging economies can adopt and implement the proposed models to even out under and overestimation errors caused by unrealistic assumptions underlying the structural models currently used worldwide.