1. Classification (Supervised Learning)
In Classification, the model learns from labeled data.
- Each input already has a correct label
- The goal is to predict that label
Examples:
- Emails → Spam or Not Spam
- Images → Cat, Dog, Car
2. Clustering (Unsupervised Learning)
In Clustering, there are no labels.
- The model finds hidden patterns
- Groups similar data points together
Examples:
- Customer data → High spenders, Budget users, Occasional buyers
Key Differences
| Feature | Classification | Clustering |
|---|---|---|
| Learning type | Supervised | Unsupervised |
| Labels | Yes | No |
| Goal | Predict categories | Discover groups |
| Output | Predefined classes | Natural clusters |
Algorithms Examples
Classification:
- Logistic Regression
- Decision Trees
- Neural Networks
Clustering:
- K-means Clustering
- Hierarchical Clustering
- DBSCAN
Summary
Classification predicts known labels; clustering discovers unknown groups.