Support Vector Machines

Predict Response Categories Using Support Vectors

The Support Vector Machines platform is available only in JMP Pro.

In JMP Pro, the Support Vector Machines (SVM) platform provides a machine learning tool for both nonlinear regression and classification. The SVM algorithm is a supervised learning algorithm that uses the training data to build a model to predict or classify new observations.

If you have a categorical response, you can visualize the model classification in the Response Profile Plot. The SVM platform also provides misclassification rates, confusion matrices, and ROC and Lift curves to help you determine how well your model fits the data. If you have a continuous response, fit statistics and actual by predicted plots are used to determine how well the model fits the data.

Figure 9.1 Response Profile Plot 

Contents

Overview of Support Vector Machines

Example of Support Vector Machines

Launch the Support Vector Machines Platform

The Support Vector Machines Launch Window

Model Launch Control Panel

The Support Vector Machine Report

Model Comparison Report

Support Vector Machine Model Report

Support Vector Machines Platform Options

Support Vector Machine Model Report Options

Additional Example of the SVM Platform

Example of Support Vector Regression for Continuous Response