Recommendation Networks and the Long Tail of Electronic Commerce
It has been conjectured that the peer-based recommendations associated with electronic commerce lead to a redistribution of demand from popular products or "blockbusters" to less popular or "niche" products, and that electronic markets will therefore be characterized by a "long tail" of demand and revenue. In this paper, we develop a novel method to test this conjecture and we report on results contrasting the demand distributions of books in over 200 distinct categories on Amazon.com. Viewing each product as having a unique position in a hyperlinked network of recommendations between product that is analogous to shelf position in traditional commerce, we quantify the extent to which a product is influenced by its recommendation network position by using a variant of Google’s PageRank measure of centrality. We then associate the average level of network influence on each category with the inequality in the distribution of its demand and revenue, quantifying this inequality using the Gini coefficients derived from the category’s Lorenz curve. We establish that categories whose products are influenced more by recommendations have significantly flatter demand distributions, even after controlling for variations in average category demand, the category’s size and measures of price dispersion. Our empirical findings indicate that doubling the average influence of recommendations on a category is associated with an average increase in the relative demand for the least popular 20% of products by about 50%, and a average reduction in the relative demand for the most popular 20% by about 12%. We also show that this effect is enhanced when there is assortative mixing in the recommendation network, and in categories whose products are more evenly influenced by recommendations. The direction of these results persist across time, across both demand and revenue distributions, and across both daily and weekly demand aggregations. Our work offers new ideas for assessing the influence of networks on demand and revenue patterns in electronic commerce, and provides new empirical evidence supporting the impact of visible recommendations on the long tail of electronic commerce.
When requesting a correction, please mention this item's handle: RePEc:net:wpaper:0903. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Nicholas Economides)
If references are entirely missing, you can add them using this form.