A Study on Time-of-Day Patterns for Internet User Using Recursive Partitioning Methods

Abstract

As of the remarkable increasing of internet users, there have been some demands of analyzing the users web accessing patterns. Internet related companies want to know the internet users web accessing patterns to promote their own products to the users. For analyzing customer’s time-of-day pattern for using internet as response vector that can be thought of as a discretized function, fitting ordinary decision trees may be unsuccessful because of their dimensionality. In this paper, we shall propose factor tree which would be more interpretable and competitive. Furthermore, using Korean internet company data, we will analyze time-of-day patterns for internet user.