Learning Product Rankings Robust to Fake Users

Abstract

Analytics in the Face of Fraudulent Data This article presents a novel online learning algorithm for identifying optimal product rankings in the presence of fake users and corrupted data. In recent years, e-commerce platforms, such as Amazon, have witnessed a growing number of fake users and click farms. These fraudulent actors seek to boost the position of certain products in the display ordering (i.e., product ranking). Further, platforms’ reliance on data analytics exacerbates the effect of these fake users as machine learning algorithms leverage user feedback to determine product rankings. In the face of these challenges, the present article departs from the status quo that is based on detecting fake users and instead proposes a robust learning methodology. More specifically, the article presents a robust online learning algorithm that converges to the optimal product ranking even when it is impossible to distinguish between real and fake users in the data.