Question

How would you use SAS Enterprise Miner to create a neural network model of your example?

Answer 1

Neural networks are a class of parametric models that can accommodate a wider variety of nonlinear relationships between a set of predictors and a target variable than can logistic regression. Building a neural network model involves two main phases. First, you must define the network configuration. You can think of this step as defining the structure of the model that you want to use. Then, you iteratively train the model.

A neural network model will be more complicated to explain to the management of your organization than a regression or a decision tree. However, you know that the management would prefer a stronger predictive model, even if it is more complicated. So, you decide to run a neural network model, which you will compare to the other models later in the example.

Because neural networks are so flexible, SAS Enterprise Miner has two nodes that fit neural network models: the Neural Network node and the AutoNeural node. The Neural Network node trains a specific neural network configuration; this node is best used when you know a lot about the structure of the model that you want to define. The AutoNeural node searches over several network configurations to find one that best describes the relationship in a data set and then trains that network.

This example does not use the AutoNeural node. However, you are encouraged to explore the features of this node on your own.

Before creating a neural network, you will reduce the number of input variables with the Variable Selection node. Performing variable selection reduces the number of input variables and saves computer resources. To use the Variable Selection node to reduce the number of input variables that are used in a neural network:

1. Select the Explore tab on the Toolbar.

2. Select the Variable Selection node icon. Drag the node into the Diagram Workspace.

3. Connect the Transform Variables node to the Variable Selection node.

   

4. In the Diagram Workspace, right-click the Variable Selection node, and select Run from the resulting menu. Click Yes in the Confirmation window that opens.

5. In the window that appears when processing completes, click Results. The Results window appears.

6. Expand the Variable Selection window.

   

   Examine the table to see which variables were selected. The role for variables that were not selected has been changed to Rejected. Close the Results window.

   Note: In this example, for variable selection, a forward stepwise least squares regression method was used. It maximizes the model R-square value. For more information about this method, see the SAS Enterprise Miner Help.

7. Close the Results window.

The input data is now ready to be modeled with a neural network. To use the Neural Network node to train a specific neural network configuration:

1. From the Model tab on the Toolbar, select the Neural Network node icon. Drag the node into the Diagram Workspace.

2. Connect the Variable Selection node to the Neural Network node.

   

3. Select the Neural Network node. In the Properties Panel, scroll down to view the Train properties, and click on the ellipses that represent the value of Network. The Network window appears. For more information about neural networks, connections, and hidden units, see the Neural Network Node: Reference documentation in SAS Enterprise Miner help.

   Change the following properties:

   • Click on the value of Direct Connection and select Yes from the drop-down menu that appears. This selection enables the network to have connections directly between the inputs and the outputs in addition to connections via the hidden units.

   • Click on the value of Number of Hidden Units and enter 5. This example trains a multilayer perceptron neural network with five units on the hidden layer.

   Click OK.

4. In the Diagram Workspace, right-click the Neural Network node, and select Run from the resulting menu. Click Yes in the Confirmation window that opens.

5. In the window that appears when processing completes, click Results. The Results window appears. Maximize the Score Rankings Overlay window. From the drop-down menu, select Cumulative Total Expected Profit.

   

   Compare these results to those from the Regression node. According to this model, if you were to solicit the best 40% of the individuals, the total expected profit from the validation data would be approximately $1900. If you were to solicit everyone on the list, then based on the training data, you could expect approximately $2300 profit on the campaign.

6. Close the Results window.