Author(s)
Daniel M. Fleder and Kartik Hosanagar
Source
NET Institute Working Paper #08-44, 2008
Summary
This paper analyzes recommender systems in the music industry.
Policy Relevance
There is a concern that recommender systems' ability to focus more powerfully on one's interests will fragment consumers. Do more popular or more obscure songs benefit from the introduction of a recommender system?
Main Points
- In contrast to concerns that users are becoming more fragmented, this paper finds that users become more similar to one another in their purchases. This increase in similarity occurs for two reasons: the taste effect and the volume effect.
- The taste effect is that consumers buy a more similar assortment of products after recommendations.
- The volume effect is that consumers simply purchase more after recommendations, increasing the chance of having common purchases with others.
