Chapter 6: Unsupervised Models—Structured Data
Chapter Overview
In this chapter, we look at unsupervised models. Unsupervised models are characterized by not having a target. As we learned in Chapters 3, 4, and 5, supervised models consider past events, or historical information, and a target, an outcome of interest that we previously know the results. Unsupervised models, on the other hand, have no target. The main goal is to find insights or to understand trends based on explanatory variables and past data. Past data can be assigned to past events, but those events will not be used as a target to train a model.
Examples of unsupervised models are clustering, association rules, link analysis, path analysis, network analysis, and text mining. ...
Get Introduction to Statistical and Machine Learning Methods for Data Science 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.
