Publications & Working Papers

We consider a class of sequential learning problems where a decision maker must learn the unknown statistical characteristics of a finite set of alternatives (or systems) using sequential sampling to ultimately select a subset of "good" alternatives. A salient feature of our problem is that system performance is governed by a set of features. The decision maker postulates the dependence on these features to be linear, but this model may not precisely represent the true underlying system structure. We show that this misspecification, if not managed properly, can lead to suboptimal performance because of a phenomenon identified as sample-selection endogeneity. We propose a prospective sampling principle—a new approach that eliminates the adverse effects of misspecification as the number of samples grows large. The proposed principle applies across a very general class of widely used sampling policies, enjoys strong asymptotic performance guarantees, and exhibits effective finite-sample performance in numerical experiments.

This paper investigates the problem of information sharing between a retail platform and a manufacturer in a supply chain. We develop a stylized model salient to which is that the product's quality is a priori unknown to customers, who can infer it from customer-generated reviews. The platform, in turn, has access to private information concerning the relationship between quality and demand, and the manufacturer can choose to acquire said information to help determine the quality of its product accordingly. Our analysis yields three main insights. First, information sharing in and of itself induces the manufacturer to improve quality. Second, under a wholesale price contract, information sharing and product reviews together have a negative effect on product quality: When each firm is able to adjust its price in response to the quality signal, it benefits the manufacturer and hinders the platform. Consequently, the presence of reviews discourages the platform from sharing information, and the manufacturer tends to produce a lower-quality product. Finally, the negative effect of product reviews on the supply chain can be mitigated when the platform can share less accurate information or when the platform and manufacturer make a commission contract, rather than a wholesale price contract.

This paper studies product ranking mechanisms of a monopolistic online platform in the presence of social learning. The products' quality is initially unknown, but consumers can sequentially learn it as online reviews accumulate. A salient aspect of our problem is that consumers, who want to purchase a product from a list of items displayed by the platform, incur a search cost while scrolling down the list. In this setting, the social learning dynamics, and hence the demand, is affected by the interplay of two unique features: substitution and ranking effects. The platform can influence the social learning dynamics by adjusting the ranking of the products to ultimately maximize the revenue collected from commission fees for sold items. To formulate the problem in a tractable form, we use a large-market (fluid) approximation and show that consumers eventually learn the products' quality and characterize the speed of learning. Armed with this backing, we formulate the platform's ranking problem in the fluid setting, where we assume the perspective of an uninformed platform that does not know the true quality vector but rather learns it through consumers' review process. We compare different ranking policies based on the worst-case regret with respect to a fully informed platform benchmark. Our analysis yields three main insights. First, a greedy policy that maximizes immediate revenue by displaying products based on current ratings may incur highly suboptimal worst-case regret, as it may relegate the most profitable products to the lowest positions in the ranking if their current rating is not high enough. Second, a simple variant of the greedy policy can sufficiently alleviate the regret by balancing the trade-off between exploration and exploitation. Third, we characterize the critical level of search cost for which the regret does not grow exponentially with the number of products.

This paper investigates how the pricing policy of a revenue-maximizing monopolist is influenced by the social learning dynamics of customers who use online reviews to estimate the quality of the product. A salient feature of our problem is that the customers' willingness to pay, and hence the demand function, evolves over time in conjunction with the online reviews. The monopolist strives to maximize its total expected revenue over a finite horizon by adjusting prices in response to these dynamics. The revenue maximization problem is studied using two different review models: a quality-based review model, where customers report their experienced quality, and a value-based review model, where reviews internalize experienced quality as well as the purchase price. To formulate the problem in tractable form, we derive a fluid model that provides a good approximation of the system dynamics when the volume of sales is large. This formulation lends itself to key structural insights into the interactions between optimal pricing policies and review dynamics. In particular, we identify critical time scales and social learning regimes that sharply separate the efficacy of dynamic pricing vis-à-vis fixed-price strategies. Furthermore, we demonstrate the impact of the quality-based and value-based review models on key structural properties of the optimal pricing policies. These structural insights are also elucidated in an illustrative simulation study based on data from an online marketplace.

We consider a problem of ordinal optimization where the objective is to select the best of several competing alternatives ("systems") when the probability distributions governing each system's performance are not known but can be learned via sampling. The objective is to dynamically allocate samples within a finite sampling budget to minimize the probability of selecting a system that is not the best. This objective does not possess an analytically tractable solution. We introduce a family of practically implementable sampling policies and show that the performance exhibits (asymptotically) near-optimal performance. Furthermore, we show via numerical testing that the proposed policies perform well compared with other benchmark policies.