Independent Variable Importance
![Independent variable importance](../images/images_m-r/out_mlp_importance_bankloan_02.jpg)
The importance of an independent variable is a measure of how much the network's model-predicted value changes for different values of the independent variable. Normalized importance is simply the importance values divided by the largest importance values and expressed as percentages.
![Independent variable importance chart](../images/images_m-r/out_mlp_importance-chart_bankloan_02.jpg)
The importance chart is simply a bar chart of the values in the importance table, sorted in descending value of importance. It appears that variables related to a customer's stability (employ, address) and debt (creddebt, debtinc) have the greatest effect on how the network classifies customers; what you cannot tell is the "direction" of the relationship between these variables and the predicted probability of default. You would guess that a larger amount of debt indicates a greater likelihood of default, but to be sure, you would need to use a model with more easily interpretable parameters.