Spreading the oprah effect: The diffusion of demand shocks in a recommendation network

Eyal Carmi*, Gal Oestreicher-Singer, Arun Sundararajan

*Corresponding author for this work

Research output: Contribution to conferencePaperpeer-review

8 Scopus citations

Abstract

We study the magnitude and persistence of the diffusion of exogenous demand shocks on an ecommerce recommendation network. The demand shocks are generated by book reviews on the Oprah Winfrey Show and in the NYTimes, and the recommendation network is generated by Amazon's copurchase network. We find a strikingly high level of diffusion of exogenous shock through such networks. Neighboring books experience a dramatic increase in their demand levels, even though they are not actually featured on the review. An average of 40% of neighbors, even 4 clicks away see a statistically significant increase in their demand levels; this effect is indicative of the depth of contagion in online recommendation networks following exogenous shocks. We also document how clustered networks "trap" a higher fraction of the contagion closer to the reviewed book, and we provide summaries of the persistence and relative magnitude of the demand inflation of the neighborhood.

Original languageEnglish
StatePublished - 2009
Event30th International Conference on Information Systems, ICIS 2009 - Phoenix, AZ, United States
Duration: 15 Dec 200918 Dec 2009

Conference

Conference30th International Conference on Information Systems, ICIS 2009
Country/TerritoryUnited States
CityPhoenix, AZ
Period15/12/0918/12/09

Keywords

  • Diffusion
  • Econometrics
  • Economics of IS
  • Electronic commerce
  • Social networks

Fingerprint

Dive into the research topics of 'Spreading the oprah effect: The diffusion of demand shocks in a recommendation network'. Together they form a unique fingerprint.

Cite this