liveBook · Manning

Mean

As explained in Grokking Machine Learning, Second Edition

The arithmetic mean obtained by dividing the sum of a set of values by their count.

The mean is the arithmetic average: add the values and divide by how many values there are. In regression, it gives a simple prediction for a group by placing a horizontal line at the labels’ average. section 9.14

A small regression example

The eight engagement labels are 7, 5, 7, 1, 2, 1, 5, and 4. Their mean is 4, so a model that gives every user the same prediction predicts 4. After splitting users younger than 35 from the rest, the group means are 6.333 and 2.6.

Regression trees use means in a repeated process:

How Grokking Machine Learning, Second Edition covers it

How deep it goes
Explains the mean through horizontal-line intuition and group calculations, then connects it to mean square error.
Examples
Uses eight user engagement values, age-based groups, horizontal predictions, and cutoff comparisons.
What you can do after
Apply it via regression trees to predict group labels and compare splits with mean square error.
How it connects
Connects the mean with regression decision trees, mean square error, and linear regression.

Also explained in

Compare how 35 books explain mean →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Grokking Machine Learning, Second Edition. The section links point to the parts of the book it draws on.