Fig. 20
From: A dynamic credit risk assessment model with data mining techniques: evidence from Iranian banks
The fuzzy Inference system of the network. Customer information was processed in Matlab R2015b before entering the model. Next, the 9000 records were entered into the model. Given that the range of the values each variable can take is different, we normalized all data by converting them into numbers between zero and one. After this stage, the training and testing data are separately entered into the software and begin to fit the model. This Fig shows the Fuzzy Inference system that is obtained in process of training the network in Matlab R2015b