Knowledge that Transforms

Consumers often learn the weights they ascribe to product attributes (“preference weights”) as they search. For example, after test driving cars, a consumer might find that he or she undervalued trunk space and overvalued sunroofs. Preference-weight learning makes optimal search complex because each time a product is searched, updated preference weights affect the expected utility of all products and the value of subsequent optimal search. Product recommendations, which take preference-weight learning into account, help consumers search. We motivate a model in which consumers learn (update) their preference weights. When consumers learn preference weights, it may not be optimal to recommend the product with the highest option value, as in most search models, or the product most likely to be chosen, as in traditional recommendation systems. Recommendations are improved if consumers are encouraged to search products with diverse attribute levels, products that are undervalued, or products for which recommendation-system priors differ from consumers’ priors. Synthetic data experiments demonstrate that proposed recommendation systems outperform benchmark recommendation systems, especially when consumers are novices and when recommendation systems have good priors. We demonstrate empirically that consumers learn preference weights during search, that recommendation systems can predict changes, and that a proposed recommendation system encourages learning. The data files and online appendix are available at https://doi.org/10.1287/mksc.2018.1144 .

Chatbot identity disclosure negatively affects customer purchases because customers perceive the disclosed bot as less knowledgeable and less empathetic.

We evaluate user-generated content as a source of customer needs and propose and test a machine-learning approach for identifying customer needs more efficiently.

Marketing Science greatly benefited from the admirable and fastidious efforts of more than 200 different individuals who provided manuscript reviews last year. Beyond those individuals already recognized on the editorial board, the editor-in-chief and guest editors of Marketing Science are indebted to the many guest editors, guest associate editors, and ad hoc reviewers who provided expert counsel and guidance on a voluntary basis. The following list acknowledges the contribution of guest editors, guest associate editors, and ad hoc reviewers who served from January 1, 2017 to December 31, 2017. Finally, our sincere appreciation to the authors, whose outstanding submissions and careful revisions make the journal the go-to resource for leading edge knowledge in quantitative marketing. K. Sudhir Yale University

This report describes entrants in the 2016 ISMS Gary Lilien Marketing Science Practice Prize Competition, representing the best examples of rigor plus relevance that our profession produces. The winner, describing a collaboration between the World Bank and a team based at the London Business School, involved a randomized control experiment to calibrate the relative effectiveness of business training on business performance of microentrepreneurs in South Africa. The other four finalists include a method to estimate the value of key word searches that allowed for cannibalization of organic search at eBay; a methodology to model and manage customer satisfaction at the National Dutch Railways; a stock-carrying algorithm to assist a fashion department store manage inventory on a store-by-store basis, implemented by Celect, an inventory-management consultant based in Boston; and an integrated marketing communications-optimization tool used by Mercedes-Benz to increase advertising effectiveness.

This paper investigates a manufacturer’s ability to influence compliance rates among its authorized online retailers by exploiting changes in the minimum advertised price (MAP) policy and in dealer agreements. MAP is a pricing policy widely used by manufacturers to influence prices set by their downstream partners. A MAP policy imposes a lower bound on advertised prices, subjecting violating retailers to punishments such as termination of distribution agreements. Despite this threat, violations are common. I uncover two key elements to improve compliance: customization to the online environment and credible monitoring and punishments. I analyze the pricing, enforcement, and channel management policies of a manufacturer over several years. During this period, new channel policies take effect, providing a quasi-experiment. The new policies lead to substantially fewer violations. With improved compliance, channel prices increase by 2% without loss in volume. The reduction in violations is particularly stark among authorized retailers with lower sales volume, those that previously operated unapproved websites, and those that have received violation notifications for the specific product before. Moreover, low service providers improve their service. At the same time, there is an increase in opportunistic behavior among top retailers, or retailers that received notifications for other products, and for less popular products via deep discounting. Data and the online appendix are available at https://doi.org/10.1287/mksc.2018.1092 .

Quota-based and partial-refund return policies abound in practice between manufacturers and their resellers. While the literature has provided insights into the design of the partial-refund policy, little attention has been directed at the design of the quota-based return policy. Accordingly, this paper explores the relative preference of a quota-based policy vis-à-vis a partial-refund policy. We do this, first, in the context of risk-neutral channel partners to identify the strategic decisions of each party and the effect of demand uncertainty on the variation of their respective profits. Our results reveal that the manufacturer faces higher profit variation (between the different demand realizations) under the quota policy. The variance in profits for the reseller is, however, higher under the partial-refund policy. We explain the source of profit variations by comparing it across different channel structures (centralized and decentralized). Next, we formally extend the model to include a disutility associated with profit variation and show that when the manufacturer has a variation-induced disutility, the partial-refund contract should be used, as it is the dominating contract. Similarly, when the retailer has a variation-induced disutility, the quota contract should be used. This is consistent with the pattern of profit variations in the risk-neutral case where the manufacturer has lower variation with the partial-refund contract while the reseller has lower variation with the quota contract. Finally, our analysis also shows how the manufacturer may employ a combination policy to better manage its own profit variation while providing adequate overstocking protection for the reseller. The online appendix is available at https://doi.org/10.1287/mksc.2018.1094 .