Multiple Linear Regression Explained

Multiple linear regression works like simple linear regression, but instead of using one input variable, it uses two or more input variables to predict a single numerical output.

Going back to the house price example, price does not depend on size alone. It also depends on location, number of bedrooms, the property's age, and nearby facilities. Multiple linear regression combines these factors to make a more accurate prediction than relying on a single variable.

How to think about it

• Multiple inputs, like size, location, and bedrooms, are combined to predict one output, like price.
• Each input variable gets its own weight, showing how strongly it influences the final prediction.
• The more relevant variables you include, the more realistic the prediction becomes, as long as the variables are actually meaningful.

Real-world example

A real estate platform predicting house prices does not just look at square footage. It considers the number of bedrooms, the neighbourhood, distance from the city centre, and the age of the building all at once to arrive at a price estimate close to what buyers would actually pay in the real market.