Fig. 17
From: A dynamic credit risk assessment model with data mining techniques: evidence from Iranian banks
Membership function of Number of Loan Repayments Past Due. The factors applied in this model as predictors are different from the previous researches. We defined these factors and a group of 10 top risk managers in several meetings approved them. Some of the factors do not change through the time, we called them certain factors. Others do, and we called them uncertain factors. We have applied fuzzy theory to uncertain factors. The fuzzy variables used to create the FIS rule base of this research were defined based on trapezoidal fuzzy numbers