Automated faceted reporting for web analytics

  • Authors:
  • Deepak Pai;Balaraman Ravindran;Shyam Rajagopalan;Ramesh Srinivasaraghavan

  • Affiliations:
  • Adobe Research, Bangalore, India;Indian Institute of Technology Madras, Chennai, India;Adobe Research, Bangalore, India;Adobe Research, Bangalore, India

  • Venue:
  • Proceedings of the 4th international workshop on Web-scale knowledge representation retrieval and reasoning
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

Traditionally, web analytics has focused on analysis and reporting of business metrics of interest to marketers, such as page views and revenue, by various dimensions of session characteristics, that can be obtained from user request. We introduce the notion of faceted reporting in the context of web analytics, where aggregated business metrics are reported grouped by a facet, a dimension along which a document could be represented. For example, in the case of e-Commerce sites, facets are typically various product attributes such as price, color, manufacturer, etc. For a typical website one could think of thousands of facets, but not all of them are equally important for the marketer in all reporting scenarios. In this work, we propose a business-metric driven scheme for automatic selection of facets for various reporting scenarios. The facet selection is done based on optimizing an objective function involving business metrics and we present our evaluation results based on multiple objective functions. We observe that, marketers' intuitive selection of useful facets is inaccurate. On the other hand automated methods proposed in this paper can highlight insights from the data.