How would you use SVM for a non-linear classification problem?

For a non-linear classification problem using Support Vector Machines (SVM), you would:

1. Apply the Kernel Trick: Use a kernel function (e.g., radial basis function (RBF), polynomial) to transform the data into a higher-dimensional space where it becomes linearly separable.
2. Train the SVM: Fit the SVM model to the transformed data using the chosen kernel to find the optimal hyperplane that separates the classes.
3. Predict and Classify: Use the trained SVM model to classify new data points based on the decision boundary established in the higher-dimensional space.