A survey on analysis of user behavior on digital market by mining clickstream data

Abstract

Data stream mining has emerged as one of the most prominent areas with its applications in various areas like network sensors, stock exchange, meteorological research and e-commerce. Stream mining is potentially an active area in which the data is continuously generated in large amounts which are dynamic, non-stationary, unstoppable, and infinite in nature. One of such streaming data generated with the user browsing tendency is Clickstream data. Analyzing the user online behavior on e-commerce Web sites is helpful in drawing certain conclusions and making specific recommendations for both the users and the electronic commerce companies to improve their marking strategies and increase the transaction rates effectively leading to enhance the revenue. This paper aims at presenting a survey of different methodologies and parameters used in analyzing the behavior of a user through Clickstream data. Little deeper, this article also outlines the methods used so far for clustering the users based on mining their interests.