Classification

Classification in Machine Learning

Overview
Classification is a type of Supervised Learning where the goal is to predict the categorical class (label) of an input data point.

Types of Classification

1. Binary Classification
Two possible classes (0 or 1).
- Spam vs Not Spam.
- Fraud vs Legitimate.
- Positive vs Negative.
- Algorithms: Logistic Regression, SVM.

2. Multi-Class Classification
Three or more mutually exclusive classes.
- Image recognition: {Cat, Dog, Bird}.
- Identifying Fruit: {Apple, Banana, Orange}.
- Constraint: An input can belong to *only one* class.
- Output Layer: Softmax (probabilities sum to 1).

3. Multi-Label Classification
An input can belong to multiple classes simultaneously.
- Movie Tags: {Action, Sci-Fi, Thriller}.
- News Article: {Politics, Economy}.
- Output Layer: Sigmoid (independent probabilities per class).

Evaluation Metrics
- Accuracy: % Correct (Bad for imbalanced data).
- Precision: How many predicted positives were actual positives? (Low False Positives).
- Recall: How many actual positives did we catch? (Low False Negatives).
- F1-Score: Harmonic mean of Precision and Recall.
- Confusion Matrix: A table showing True methods vs Predicted values.

Classification is the workhorse of enterprise AI.