Supervised Learning is a type of machine learning where the model learns using labeled data—meaning each input comes with the correct output.
Simple Definition
In Machine Learning, supervised learning means:
The algorithm is trained on input-output pairs and learns to predict the correct output for new, unseen data.
Key Idea
- Data includes inputs + correct answers (labels)
- Model learns a mapping function: input → output
- Goal is to make accurate predictions
Types of Supervised Learning
1. Classification
Output is a category or class
Example:
- Spam vs Not Spam email
Popular algorithms:
- Logistic Regression
- Decision Tree
- Support Vector Machine
2. Regression
Output is a continuous value
Example:
- Predicting house price
Popular algorithms:
- Linear Regression
- Random Forest
Real-Life Examples
- Email spam detection
- Predicting stock prices
- Credit risk assessment
- Image recognition (cat vs dog)
How It Works (Step-by-Step)
- Collect labeled dataset
- Train the model using known outputs
- Test the model on new data
- Improve accuracy using tuning
Easy Analogy
Imagine a teacher teaching a child:
- Teacher shows questions with answers
- Child learns patterns
- Later, child solves similar questions on their own
Supervised vs Unsupervised (Quick View)
| Feature | Supervised Learning | Unsupervised Learning |
|---|---|---|
| Data | Labeled | Unlabeled |
| Goal | Predict output | Find patterns |
| Example | Price prediction | Customer grouping |