Building Your First Machine Learning Model with Linear Regression Using Ordinary Least Square

Author(s): Souradip Pal

Originally published on Towards AI.

Let’s deep dive into the math and code it up from scratch

This member-only story is on us. Upgrade to access all of Medium.

Suppose you’re on the hunt for a new apartment in your dream location — be it Thailand, Japan, or London. You’ve got the money (let’s skip the how for now), but how do you decide on the right price? You don’t want to just rely on the seller’s word, right? How about staying a step ahead by using a machine learning model to predict the price, ensuring you negotiate like a pro?

To build this model, you’ll need a dataset with past prices in that area. Let’s assume you’ve somehow acquired this elusive data. You now have features like land area, the number of rooms, the number of bathrooms, and living room dimensions — along with the all-important price column. Naturally, each of these features will influence the price in different ways.

Now, let’s simplify. For the sake of understanding, we’ll just consider the relationship between the number of rooms and the apartment price.

Image showing a sample dataset containing only three points, with Y axis showing the PRICE in 1 unit = $100K and X axis showing the number of rooms. Source- Image by the Author

Imagine plotting this relationship on a… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI