Clustering Analysis of Clickstream Data in Consumer Path to Purchase

• Activity Number: 129
• Type: Contributed
• Date/Time: Monday, August 5, 2013 : 8:30 AM to 10:20 AM
• Sponsor: Section on Statistics in Marketing
• Author(s): Mark Irwin*+ and Amit Phansalkar
• Companies: Compete and Compete
• Keywords: Click stream data ; Touch points ; Clustering ; Path to Purchase

Abstract

Marketers are increasingly interested in understanding how consumers use the internet to research during their shopping process, where they can they be targeted, what resources they used, what brands are in there consideration set, and how intensely are they shopping prior to purchase. The analysis of click stream data is a useful tool in answering these questions.

We will present a case study that uses frequency and order of visiting touch points, the amount of time they spend on each of them, and the time between visits to consecutive touch points in their click stream data to cluster consumers into different segments. Classes of touch points in an analysis include retailer, brand, review, social media, and search sites, among others. Clustering techniques for data of this type will be discussed and the power of the approach will be exhibited with recent examples involving consumer electronic purchases. We will present how the Marketer benefited in creating a more successful brand strategy using the analysis.