Blockbuster culture's next rise or fall: The impact of recommender systems on sales diversity

摘要

Recommender systems use data on purchases, product ratings and user profiles to predict the products best suited to a specific user and help find niche products among the seemingly endless popular (hit) products. In turn they may create a rich-get-richer effect for popular and vice versa for the unpopular ones. This aspect is probed in detail to show how a basic design choice can affect the outcome and thus, managers can choose recommender designs which are more consistent with their sales goals and consumer preferences.