LSVM Model Nugget (interactive output)

After running an LSVM model, the following output is available.

Model Information

The Model Information view provides key information about the model. The table identifies some high-level model settings, such as:
  • The name of the target specified on the Fields tab
  • The model building method specified on the Model Selection settings
  • The number of predictors input
  • The number of predictors in the final model
  • The regularization type (L1 or L2)
  • The penalty paramater (lambda). This is the regularization parameter.
  • The regression precision (epsilon). Errors are accepted if they are less than this value. A higher value may result in faster modeling, but at the expense of accuracy. It is only used only if the measurement level of the target field is Continuous.
  • The classification accuracy percentage. This is only applicable for Classification.
  • The average squared error. This is only applicable for Regression.

Records Summary

The Records Summary view provides information about the number and percentage of records (cases) included and excluded from the model.

Predictor Importance

Typically, you will want to focus your modeling efforts on the predictor fields that matter most and consider dropping or ignoring those that matter least. The predictor importance chart helps you do this by indicating the relative importance of each predictor in estimating the model. Since the values are relative, the sum of the values for all predictors on the display is 1.0. Predictor importance does not relate to model accuracy. It just relates to the importance of each predictor in making a prediction, not whether or not the prediction is accurate.

Predicted by Observed

This displays a binned scatterplot of the predicted values on the vertical axis by the observed values on the horizontal axis. Ideally, the points should lie on a 45-degree line; this view can tell you whether any records are predicted particularly badly by the model.

Note: Predictor importance may take longer to calculate for LSVM and SVM than for other types of models. Selecting this option may slow performance, particularly with large datasets.

Confusion Matrix

The confusion matrix, sometimes referred to as the summary table, shows the number of cases correctly and incorrectly assigned to each of the groups based on the LSVM analysis.