Home // ALLDATA 2017, The Third International Conference on Big Data, Small Data, Linked Data and Open Data // View article

Analyzing Browsing and Purchasing Across Multiple Websites Based on Latent Dirichlet Allocation

Authors:
Nadine Schröder
Andreas Falke
Harald Hruschka
Thomas Reutterer

Keywords: Topic Models;Latent Dirichlet Allocation; Internet Usage and Purchasing Behaviour; Behavioral Segmentation

Abstract:
The increasing importance of online channels for retailers and service providers is paralleled by a rising interest in gaining insights into the customer journey to online purchases. Most attempts to shed light to this issue are restricted to data available for only few particular sites. Our research focuses on mining online shoppers' website visitation patterns across 472 individual websites. We propose a methodological framework to uncover latent interests which we assume to underlie observable online browsing behavior. Using one year of clickstream data for a random sample of comScore panelists, we show that there is heterogeneity among shoppers regarding online browsing habits, combinations of latent interests, and their conversion into online purchases. Our analysis finds that a relatively small fraction of online shoppers realizes 70% of online spending. In addition, we detect substantial segment-specific differences of shopping behavior with respect to 59 product categories.

Pages: 40 to 44

Copyright: Copyright (c) IARIA, 2017

Publication date: April 23, 2017

Published in: conference

ISSN: 2519-8386

ISBN: 978-1-61208-552-4

Location: Venice, Italy

Dates: from April 23, 2017 to April 27, 2017