How Algorithmic Confounding in Recommendation Systems Increases Homogeneity and Decreases Utility

TL;DR

This paper investigates how algorithmic confounding in recommendation systems creates feedback loops that homogenize user behavior and reduce utility, highlighting the need for better evaluation methods.

Contribution

The study introduces simulation-based analysis showing how confounded data leads to homogenized user behavior and decreased utility in recommendation systems.

Findings

Confounded data homogenizes user behavior

Homogenization does not increase system utility

Simulations demonstrate feedback loop effects

Abstract

Recommendation systems are ubiquitous and impact many domains; they have the potential to influence product consumption, individuals' perceptions of the world, and life-altering decisions. These systems are often evaluated or trained with data from users already exposed to algorithmic recommendations; this creates a pernicious feedback loop. Using simulations, we demonstrate how using data confounded in this way homogenizes user behavior without increasing utility.