Kartik Hosanagar

Who they are

Hosanagar is given at the University of Pennsylvania on the 2019 Information Systems Research paper and in Carnegie Mellon University's release about it. In 2009 he and Daniel Fleder used an analytical model and simulations in Management Science to show that some recommenders can push each person towards new products while pushing users towards the same products, so individual diversity can rise while aggregate diversity falls. They concluded that design choices shape which way the effect runs.

In 2019 he and Dokyun Lee reported a randomised field experiment on a major North American retailer's website, covering 1,138,238 users and 82,290 products. Collaborative filtering was associated with lower aggregate sales diversity than no recommendations, while individual shoppers explored more. Niche items gained sales in absolute terms but lost share. According to Carnegie Mellon's release, the bottom 80 per cent of products took 37 per cent of sales without a recommender and 27 per cent with one.

Key papers

Fleder, D., & Hosanagar, K. (2009). "Blockbuster culture's next rise or fall: the impact of recommender systems on sales diversity." Management Science, 55(5), 697-712. doi:10.1287/mnsc.1080.0974.

Lee, D., & Hosanagar, K. (2019). "How do recommender systems affect sales diversity? A cross-category investigation via randomized field experiment." Information Systems Research, 30(1), 239-259. doi:10.1287/isre.2018.0800.

Key ideas

See Sales Diversity and Recommender Systems.

---