This screen shows the parameters the prediction will use when training. Among other things, parameters are used to determine the number and type of walk-forward tests, as well as the training set size and the training objective (training by profit or error). The defaults set are very useful for a broad variety of problems and should be used unless you consider yourself an advanced user. For more information on training sets, walk-forward tests, and objectives see Neural Network – Network Criteria Discussion
This screen may or may not be displayed depending upon the currently selected Prediction Wizard Interface Options. If displayed, the list will show only the parameters whose interface options have been selected. All other parameters are set to their default values and do not appear in the list when the corresponding interface option has not been selected. Press the Options button to change the Prediction Wizard Interface Options. For more information see Prediction Wizard Interface Options.
If you wish to change any of these parameters:
- Press the Change Prediction Parameters button.
When you are satisfied with the parameters the prediction will use when training press the Next button to proceed to the next wizard screen.
Topics of Interest:
What are Neural Networks?
Neural Network – Network Criteria Discussion
Troubleshooting Your Model – What to Do if You Feel You Haven’t Been Successful