On Detecting Frauds in Comparison-Shopping Services

Sang-Chul Lee, Christos Faloutsos, Dong-Kyu Chae, Sang-Wook Kim

Abstract: In comparison-shopping services (CSS), there exist frauds who perform excessive clicks on a target item in order to boost the popularity of it. In this paper, we introduce the problem of detecting frauds in CSS and propose three anomaly scores designed based on click behaviors of users in CSS.