Logistic Regression Simply Explained in 5 minutes

A simple and gentle introduction to Logistic Regression with Python code & a working example

Figure made by the author using https://sketch.io/sketchpad/

Hi all. Thanks for your interest in my article. Let’s get started!

1. Short Introduction

Logistic regression is a machine learning technique with origins from the field of statistics. It is a really widely used method for binary classification problems (note: it is not a regression method as its name suggests) but can also be used for multi-class classification problems (e.g. more than 2 classes/labels with one-vs-rest implementation).

Logistic regression is named after the function used at the core of the method, the logistic function.

2. Core of the method

The logistic function, also called the sigmoid function was developed by statisticians to describe properties of population growth in ecology, rising quickly and maxing out at the carrying capacity of the environment [1]. It is an S-shaped curve that can take any real-valued number and map it into a value between 0 and 1 (but never, mathematically speaking, exactly equal to those limits).

Logistic regression…