The algorithm used for Anomaly Detection models is One-Class SVM.
SVM supports two kernel functions: Linear and Gaussian. You can pick one of the kernel functions or you can let the system determine the kernel function. The default is to let the system determine the kernel function.
If you let the system determine the kernel function, you can modify the following settings:
The settings have the same meanings as they do for SVM classification models.
Outlier Rate is specific to anomaly detection problems. If you have some knowledge that the number of anomalous cases is a certain percentage of your population, you set Outlier Rate to that percentage, and the model will identify approximately that many anomalous cases when applied to the general population. The default value is 10%.
For more information, see SVM Kernel Functions.
If you specify the Gaussian kernel, you can also change the following settings:
The settings are described in detail in Support Vector Machine Settings.
Click OK to continue.
Copyright © 2006, 2008, Oracle. All rights reserved.