Working Paper

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

Guy Aridor, Duarte Gonçalves, Daniel Kluver, Ruoyan Kong, Joseph Konstan
CESifo, Munich, 2022

CESifo Working Paper No. 10129

We conduct a field experiment on a movie-recommendation platform to identify if and how recommendations affect consumption. We use within-consumer randomization at the good level and elicit beliefs about unconsumed goods to disentangle exposure from informational effects. 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. Our results highlight the importance of recommender systems’ informational role when considering policies targeting these systems in online marketplaces.

CESifo Category
Industrial Organisation
Economics of Digitization
Keywords: recommender systems, information acquisition, field experiment
JEL Classification: D830, D470, D120, L150, M370