The Economics of Recommender Systems: Evidence from a Field Experiment on MovieLens

Guy Aridor, Duarte Goncalves, Daniel Kluver, Ruoyan Kong, Joseph Konstan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We conduct a 6 month field experiment on a movie-recommendation platform to identify if and how recommendation systems affect consumption. We use within-consumer randomization at the good level and elicit beliefs about unconsumed goods to disentangle exposure from informational effects. We have three experimental groups: (a) control, (b) exposed, and (c) recommended + exposed goods where only goods in (c) are recommended and we elicit beliefs about goods in (b) and (c). Comparing across these treatment arms we find recommendations increase consumption beyond its role in exposing goods to consumers. We provide support for an informational mechanism: recommendations affect consumers' beliefs, which in turn explain consumption. Recommendations reduce uncertainty about goods consumers are most uncertain about and induce information acquisition. Finally, we find evidence for spatial correlation in beliefs.

Original languageEnglish (US)
Title of host publicationEC 2023 - Proceedings of the 24th ACM Conference on Economics and Computation
PublisherAssociation for Computing Machinery, Inc
Pages117
Number of pages1
ISBN (Electronic)9798400701047
DOIs
StatePublished - Jul 9 2023
Event24th ACM Conference on Economics and Computation, EC 2023 - London, United Kingdom
Duration: Jul 9 2023Jul 12 2023

Publication series

NameEC 2023 - Proceedings of the 24th ACM Conference on Economics and Computation

Conference

Conference24th ACM Conference on Economics and Computation, EC 2023
Country/TerritoryUnited Kingdom
CityLondon
Period7/9/237/12/23

Keywords

  • field experiment
  • information acquisition
  • recommender systems

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Economics and Econometrics
  • Computational Mathematics
  • Statistics and Probability

Fingerprint

Dive into the research topics of 'The Economics of Recommender Systems: Evidence from a Field Experiment on MovieLens'. Together they form a unique fingerprint.

Cite this