SVM-Hyperparameter-Tuning

This repository show how the Support vector machine model perform with different Gamma and C value.

Gamma in SVM

• Low value indicates a large similarity radius which result in more points being grouped together
• For High values , the points need very close to each other in order to be considered in same group.

C in SVM

• If c is small, the penalty for missclassified points is low so a decision boundary with large margin is chosen.
• if c is large, SVM tries to minimize the number of missclassified example due to high penalty which result in a decision boundary with a smaller margin.

Dataset Used

200 data points

Change in Value of Gamma

Change in Value of C