Interactive Support Vector Machine (SVM) Sandbox

Hyperplane (Decision Boundary)

Margins (Gutters)

Support Vectors

Confusion Matrix (Training Set Evaluation)

Predicted Red (+)

Predicted Blue (-)

Total

Actual Red

0 0.0% True Red (TP)

0 0.0% False Blue (FN)

Actual Blue

0 0.0% False Red (FP)

0 0.0% True Blue (TN)

Total

1. Select Class to Plot

Class +1 (Red) Class -1 (Blue)

2. Classification Error Tolerance Mode

Hard Margin (No Errors) Soft Margin (Allow Slack)

Hard margin forces absolute separation (will report non-separable on overlapping points). Soft margin uses relaxation slack to find a boundary amidst noise.

3. Select Target Focus Class for Metrics Calculations

Red Class (+) Blue Class (-)

Derived Evaluation Metrics Calculations

Accuracy

0.0%

Precision

0.0%

Sensitivity (Recall)

0.0%

Specificity

0.0%

Model Status: Ready
Click inside the data plane grid to manually plot coordinates. Try making two separate clusters to generate an optimal boundary corridor!

💡 Classroom Experiment: Toggle over to **Soft Margin** when working with messy or non-separable datasets. Notice how the model avoids crashing and instead constructs a stable decision corridor, minimizing error using an automated subgradient optimization routine!