Social Learning from Online Reviews with Product Choice

Product choice when consumers engage in social learning has significant implications on learning outcomes and on the information accumulation rate. In many practical settings, consumers can choose which product to buy, if any, among several possible alternatives. The quality of these products may be unknown to consumers, but online platforms provide product reviews so that, as time goes by, customers accumulate information about the products' quality. This paper studies a model where consumers estimate the quality of products from online binary product reviews (like/dislike), and subsequently make a choice among competing alternatives using a multinomial logit model. We explore the impact of choice on the learning outcome, and show that consumers correctly learn the ranking of the product qualities, but not the actual quality vector, and provide the conditions that allow consumers to get arbitrarily close to the truth. Using a large market (fluid model) approximation, we study how choice and product parameters affect learning speed and derive some intuition on the primitives that matter the most. Finally, we address the following control problem: assuming that consumers incur search costs that are increasing in the ordering in which products are displayed, what is the ordering policy that the platform should use to speed up learning and purchases? We assume the perspective of an uninformed platform that does not know the true quality vector but rather learns about it through consumers' review process and compare different heuristic ranking policies based on the worst-case regret with respect to a fully-informed platform benchmark.Our results highlight that greedy policy that maximize immediate revenues by displaying products based on current ratings may incur highly suboptimal worst-case regret, as they may relegate the most profitable products to the lowest positions in the ranking if their current rating is not high enough. On the other hand, exploratory policies that systematically induce costumers to explore each product in order to quickly discover the products' true qualities, to exploit this information later on, guarantee that the true quality of each product is discovered in nearly constant time, which results in significantly lower worst-case regret compared to the greedy policies