Optimizing Click-through in Online Rankings for Partially Anonymous Consumers

(Dr. Babur De Los Santos with Sergei Koulayev, invited for third round review, Marketing Science)


The vast amount of information available online has revolutionized the way firms present consumers with product options. Presenting the best alternatives first reduces search costs associated with a consumer finding the right product. We use novel data on consumer click-stream behavior from a major web-based hotel comparison platform to estimate a random coefficient discrete choice model and propose an optimal ranking tailored to anonymous consumers that differ in their partially revealed price sensitivity. We are able to customize rankings by relating price sensitivity to request parameters, such as the length of stay, number of guests, and day of the week of the stay. In contrast to a myopic popularity-based ranking, our model accounts for the rapidly changing prices that characterize the hotel industry and consumers’ search refinement strategies, such as sorting and filtering of product options. We propose a method of determining the hotel ordering that maximizes consumers’ click-through rates (CTR) based on the information available to the platform at that time, its assessment of consumers’ preferences, and the expected consumer type based on request parameters from the current visit. We find that CTRs almost double when consumers are provided with customized rankings that reflect the price/quality trade-off inferred from the consumer’s request parameters. We show that the optimal ranking results in an average consumer welfare 173 percent greater than in the default ranking.

Download This Paper

Related posts: