Integrating purchase patterns and traversal patterns to predict HTTP requests in e-commerce sites

Abstract

The success of an e-commerce (electronic commerce) site is measured in terms of the number of users visiting the site. A survey of essential qualities for a successful EC site suggests that reduced user perceived latency is the second most important quality after good site navigation quality. The most successful approach towards reducing user perceived latency has been the extraction of path traversal patterns from past users access history to predict future user traversal behavior and to prefetch the required resources. However this approach is suited for only non-EC sites where there is no purchase behavior. In this paper we describe a new approach to predict user behavior in EC sites. The core of our approach involves extracting knowledge from integrated data of purchase and path traversal patterns of past users to predict the purchase and traversal behavior of future users. Simulations were conducted using synthetic data, which showed that the proposed model produces more accurate modeling of the user behavior.