The Ex-Ante View of Recommender System Design
share
Recommender systems (RS) are traditionally deployed in environments where users are uncertain about their preferences and thus face a problem of choice under uncertainty, but most popular design approaches ignore this fact. We argue that predicting and modeling consumer choice in these contexts can improve the usefulness of RS and reframe the RS problem as providing useful information to help reduce user uncertainty as opposed to simply predicting user preferences. Using a theoretical model, we show how this insight can be utilized to design RS that mitigate negative consequences such as filter bubble and user-homogenization effects as well as to better understand the role that RS play in contributing to these phenomena.
READ FULL TEXT
