Chapter 11. How to Make Simple Predictions: Linear Regression

Those who have knowledge, don’t predict. Those who predict, don’t have knowledge.

—Lao Tzu(Chinese philosopher and founder of Taoism, sixth century BC)

In machine learning, regression leverages a technique borrowed from statistics to predict output values. Along with classification, regression is the typical choice for problems in which the solution consists of predicting output starting from some input. Classification and regression do the same job but with one important difference. The output of regression is numeric and in a continuous range, whereas the output of classification is categorical and based on values that fall in a discrete set.

In all the chapters in Part III, “

Get Introducing Machine Learning now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.