A System Dynamics Model For Credit Risk Modelling And Simulation: The Case Of Licensed Credit Reference Bureaus In Kenya

Abstract

Credit risk modelling and analysis are needed in finance and have over many years become active parts of research, motivating statistical modelling. Because of the high numbers of borrowers who fail to fulfil their loan repayments, credit reference bureaus (CRBs) have existed for quite some time especially in countries that have long histories of hosting multinational companies. However, the current standards for regulating how credit risk is quantified have often used assumptions that don’t match the reality. This study deals with modelling and estimating through simulating the risk from borrowing activities as it relates to CRBs. Data was collected from annual default reports from the CBK, CRBs and major financial institutions over three years (2018, 2019, and 2020). The study also used focus group discussions to establish baseline levels of default factors. A sample of 12 participants was drawn from the total population of CRB staff members performing the core functions of credit risk determination. The study data was collected using document analysis and Focus Group Discussions (FGDs) to gather historical and current data both qualitative and quantitative. Using the advanced system dynamics approach, the study conducted simulations with starting values from real world scenarios to produce actual measurements of defaulting risk. The model involves analysing the dynamics of common factors which influence the borrower’s ability to repay loans. Descriptive analysis was through tabled summaries and bar charts, and explorative analysis applied Causal loop diagrams (CLDs). The simulation was conducted with the aid of graphical output generated from calibration of stock-and-flow diagrams. Through simulations, the study demonstrated how influential parameters of the model are estimated and provided statistical evidence that the model fits the Kenyan CRBs situation better than other often used techniques. The information gained from this study will benefit the government, the Central bank of Kenya (CBK), research scholars and other major financial institutions around the country.