Credit Card Use. Consider the following hypothetical bank data on consumers' use of credit card credit facilities in Table 11.3 . Create JMP data, and create a neural network like that used for the tiny data example. Use the default validation method (Holdback Portion).

a. How does the model perform on the validation set?

b. How many parameters are estimated to build this model?

c. Use the Categorical Profiler to explore how the predicted response changes as you change values of the predictors. Describe what you observe.

d. Fit another neural network to this same data.

i. Describe the differences between this model and the first model you generated.

ii. Why do the results differ?

Transcribed Image Text:

TABLE 11.3 Data for Credit Card Example and Variable Descriptions Years 4 Salary 43 18 1 65 53 3 95 15 88 6 112 Used Credit 0 1 0 0 1 1