Chapter 3. Finding Patterns in the Noise – Clustering and Unsupervised Learning

One of the natural questions to ask about a dataset is if it contains groups. For example, if we examine financial market data consisting of stock price fluctuations over time, are there groups of stocks that fall and rise with a similar pattern? Similarly, for a set of customer transactions from an e-commerce business we might ask if are there groups of user accounts distinguished by patterns of similar purchasing activity? By identifying groups of related items using the methods described in this chapter, we can understand data as a set of general patterns rather than just individual points. These patterns can help in making high-level summaries at the outset of a predictive modeling project, or as an ongoing way to report on the shape of the data we are modeling. The groupings produced can serve as insights themselves, or they can provide starting points for the models we will cover in later...