The Power of Ranking: Quantifying the Effects of Rankings on Online Consumer Search and Choice∗

When consumers face many options, intermediaries can help by ranking them, which in turn can influence how consumers search and what they ultimately purchase. To understand such influence, it is crucial to separate the role the ranking plays in consumer choices from other characteristics of the firm. As the ranking is endogenous, separately identifying the role of the ranking is challenging. In this paper, I identify the causal effect of rankings by using a data set on hotel searches that includes both a random ranking and the default ranking of a popular online travel agent. I show that rankings affect both clicks and purchases, but that conditional on a click, consumers do not derive any additional utility from purchasing from a higher ranked hotel. In addition, the data permits testing two common modeling assumptions found in the literature: that position mainly affects search costs and that consumer search sequentially, both of which are supported by the data. To quantify the effect of rankings on consumer choices, I estimate a sequential search model that accounts for the order in which consumers search. This model reveals that search cost estimates ignoring the endogeneity bias of position are upward biased. Using this model’s search and preference parameter estimates, I construct several counterfactuals of interest comparing the value of the default ranking with the optimal ranking for consumers, hotels and the intermediary.