داوود نوروزی

The core goal of this study was to simulate the share and predict the current and non-current receivables in Shahr Bank using an agent-based approach. To this end, we employed the data related to the examined features in 11 bank branches aimed at determining the degree of importance of each of the factors affecting the repayment behavior of borrowers using the C5.0 algorithm, the decision tree method, and the simulation process in NetLogo software. We utilized the comparison of the repayment status of a sample of 100 customers over the past year (12 months ago) and at present aimed at assessing the simulated model. The estimation results of the simulation model, as well as the real findings, suggested that the number of type 1 customers (with active repayment status) has decreased during the last 12 months and the number of type 2 customers (with past due repayment status) has enhanced. If the economic recession conditions continue the same way, and considering the low effect of the recession conditions on the businesses of the bank''s customers in the next four years, then, the ratio of the bank''s current customers will decrease from about 89% to about 81%, while the ratio of the past-due customers of the bank will increase to more than double to about 13%. In the next step, we tried to simulate the future situation of the ratio and the share of the current bank customers'' claims in the next 4 years.