Regression And Classification

Regression vs Classification

In empirical modelling, we mainly do two kinds of prediction:

Predicting numerical values

Predicting by classifying objects or situations

These two ideas lead to regression and classification.

REGRESSION

Predicting a Number

Regression is used when the output is a continuous numerical value.

Output is continuous
Decimals are allowed
The task is about calculating an estimate, not choosing a label

Examples:

Marks = 72.4
Temperature = 29.5 °C
House price = ₹52,40,000
Distance = 12.3 km

Typical question: How much? How many?

CLASSIFICATION

Predicting a Category

Classification is used when the output belongs to a fixed category.

Output consists of fixed classes
Output values are discrete
Decimals do not apply
The task is about deciding a label, not calculating a number

Examples:

Email: Spam or Not Spam
Student: Pass or Fail
Disease: Yes or No
Image: Cat or Dog
Weather: Hot or Cold

Typical question: Which one? Yes or No?

Conclusion

If the output is a numerical value that can vary continuously, it is a regression problem.
If the output belongs to a fixed set of categories, it is a classification problem.

Examples of Regression and Classification

Examples of Regression Problems

Regression problems involve predicting a continuous numerical value.

House price estimation
Estimating the selling price of a house using floor area, location, and age of the building.
Weather measurement
Predicting temperature values, rainfall quantity, or wind speed.
Student performance analysis
Estimating marks or GPA based on study hours and attendance.
Sales forecasting
Predicting future sales revenue using historical sales data.
Fuel efficiency estimation
Estimating fuel consumption from engine size and vehicle weight.

Examples of Classification Problems

Classification problems involve assigning data to a fixed set of categories.

Email filtering
Classifying emails as spam or not spam.
Medical diagnosis
Classifying patients as disease positive or disease negative.
Image recognition
Identifying whether an image contains a cat, dog, or another object.
Credit risk evaluation
Classifying loan applicants as low risk or high risk.
Student result classification
Classifying students as pass or fail.

Need help with mathematics?

School, college or engineering — if you are stuck, confused or need help, reach out to us. We will guide you step by step and make concepts simple.

Choose how you want to contact us:

Regression vs Classification

Predicting a Number

Predicting a Category

Examples of Regression and Classification

Need help with mathematics?

Available Formula Sheets