Work

How algorithmic confounding in recommendation systems increases homogeneity and decreases utility

Year: 2018

Type: conference-paper

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.

Source: ACM Conference on Recommender Systems (RecSys)

DOI: 10.1145/3240323.3240370

Authors: Allison J. B. Chaney, Brandon M. Stewart, Barbara E. Engelhardt

Institution: Princeton University

Language: English

Topic: Recommender Systems and Techniques

Subfield: Information Systems

Field: Computer Science

Domain: Physical Sciences

Open Access status: bronze

Funders: National Science Foundation, National Institutes of Health, National Heart, Lung, and Blood Institute

Awards: Epigenetic fine-mapping of cardiometabolic disease loci in the human liver, G5520316217, G6671297155, RAPID: Innovative Use of Vegetation to Mitigate Overtopping Hazard of Levees due to Hurricane-induced Waves