Skip to main content

Table 4 Predictive power of the model. This table shows the predicted values of the probability for the dependent variable Y based on being above or below the threshold, in contrast with the actual values observed in the model data. It shows that the degree of sensitivity and degree of diagnosis of ANFIS in the model data were 87.08% and 91.03%, respectively

From: A dynamic credit risk assessment model with data mining techniques: evidence from Iranian banks

Real estimate observation Medium risk customers High risk customers Total
P(Y) < =0.37 6061 163 6224
P(Y) > 0.37 597 1099 1696
Total 6658 1262 7920
Correct 6061 1099 7160
Correct percent 91.03% 87.08% 90.04%
Incorrect percent 8.96% 12.91% 9.5%