Bayesian Social Learning from Consumer Reviews

28 Pages Posted: 13 Jul 2013 Last revised: 21 Jan 2019

See all articles by Bar Ifrach

Bar Ifrach

Uber Technologies Inc. - Uber Freight

Costis Maglaras

Columbia University - Columbia Business School, Decision Risk and Operations

Marco Scarsini

Luiss University Dipartimento di Economia e Finanza

Anna Zseleva

Tel Aviv University

Date Written: January 21, 2019

Abstract

Motivated by the proliferation of user-generated product-review information and its widespread
use, this note studies a market where consumers are heterogeneous in terms of their willingness-to-pay for a new product. Each consumer observes the binary reviews (like or dislike) of consumers who purchased the product in the past and uses Bayesian updating to infer the product quality. We show that the learning process is successful as long as the price is not prohibitive and therefore at least some consumers, with sufficiently high idiosyncratic willingness-to-pay, will purchase the product irrespective of their posterior quality estimate. We examine some structural properties of the dynamics of the posterior beliefs.
Finally, we study the seller's pricing problem, and we show that, if the set of possible prices is finite, then a stationary optimal pricing policy exists. If putting one item on the market involves a constant cost, then under this optimal policy, learning fails with positive probability.

Keywords: social learning, online reviews

JEL Classification: D49, D83

Suggested Citation

Ifrach, Bar and Maglaras, Costis and Scarsini, Marco and Zseleva, Anna, Bayesian Social Learning from Consumer Reviews (January 21, 2019). Available at SSRN: https://ssrn.com/abstract=2293158 or http://dx.doi.org/10.2139/ssrn.2293158

Bar Ifrach

Uber Technologies Inc. - Uber Freight ( email )

685 Market Street
San Francisco, CA 94105
United States

Costis Maglaras

Columbia University - Columbia Business School, Decision Risk and Operations ( email )

New York, NY
United States

Marco Scarsini (Contact Author)

Luiss University Dipartimento di Economia e Finanza ( email )

Viale Romania 32
Rome, RM 00197
Italy

Anna Zseleva

Tel Aviv University ( email )

Ramat Aviv
Tel-Aviv, 6997801
Israel

HOME PAGE: http://annazseleva.com

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
613
Abstract Views
2,763
Rank
80,234
PlumX Metrics