Search

This paper introduces a new decision support tool to optimize advertising campaigns for new product launches based on learnings from an ex post analysis of prior campaigns.

Georgia Aquarium (GA), a non-profit organization, is the world’s second largest aquarium (by water volume) and is among the most popular tourist destinations in the United States. Recently GA management has observed that the organization’s growth trajectory is stagnating. While other aquariums face a similar trend, GA wants to be proactive and reverse this direction. They face a multifaceted business challenge involving four conflicting objectives: (1) How to increase revenues without increasing ticket prices; (2) how to increase attendance without compromising visitor satisfaction; (3) how to increase the impact of media investments without spending more; (4) how to attract customers with long-term value potential. To address these challenges, we developed an integrated approach consisting of multiple marketing science models including Data Envelopment Analysis, Competition Analysis, Spatial Analysis, Media Optimization Analysis, and Pass Holder Lifetime Net Revenue Analysis. Based on the findings of our analyses and the parameter estimates of our models, GA proceeded with a field implementation to validate our suggestions. As a result, they realized a 10% increase in attendance and a 12% increase in revenue in 2013, thereby enhancing their bottom line and growth. Data, as supplemental material, are available at http://dx.doi.org/10.1287/mksc.2015.0932 .

The purpose of this paper is to describe the implementation of a category management tool known as Category Optimizer™ at Foster's Wine Estates Americas for one of its brands, the Beringer California Collection. Foster's was facing a common management problem: harnessing its portfolio of Beringer California Collection wines to increase profitability, improve its competitive position, and defend against a disruptive new entrant in the U.S. wine market called Yellow Tail. Category Optimizer combines the parsimony of an internal market structure with the advances that have been made in assortment planning in operations research, assortment and stock-keeping-unit–level modeling, mixed logits, and the marketing literature on the perceptions of variety of assortment to develop and estimate a model on readily available store scanner data. The model subsequently uses these results to inform strategic and tactical decision making. This approach led to recommendations that initially seemed counterintuitive; the normal response would be for Foster's to consider lowering prices to maintain share and volume, a strategy not inconsistent with many of the recommendations of past models. However, considering the additional degrees of freedom that a product range offered for defense, we demonstrated that a combination of price increases together with the introduction of a volume-flanker product in a new channel would improve profits, increase revenue, and protect and enhance market share. These were successfully implemented in early 2008, earning rich dividends for the company; increasing profitability by 70%, revenue by 3%, and earnings before interest and taxes by 8.5%; and having a positive impact on its brand ranking. In fact, in 2008, it debuted as sixth among the international wine brands. It also managed to play an important role in deposing Yellow Tail, the market share leader, from its dominant position. We conclude the paper by providing examples of other companies where this approach has also been successfully implemented and by discussing some avenues for future research.

This paper describes a new data set available to academic researchers (at the following website: http://mktsci.pubs.informs.org ). These data are comprised of store sales and consumer panel data for 30 product categories. The store sales data contain 5 years of product sales, pricing, and promotion data for all items sold in 47 U.S. markets. In two U.S. markets, the store level data are supplemented with panel-level purchase data and cover the entire population of stores. Further information is available regarding store characteristics in these markets. We address several potential applications of these data, as well as the access protocol. The data set described in this paper is maintained by IRI. Any fees charged by IRI for the distribution of the data set will be used for the continual maintenance and updating of the data. Scholarships to cover IRI's fees (for those who need it) are available through the INFORMS Society for Marketing Science (ISMS). Please see the website above for further details.

In addition to retailing new vehicles, automotive manufacturers in the United States sell millions of vehicles through leasing and to fleet customers every year. The majority of these vehicles are returned to the automotive manufacturers at the end of the contracted term and must be “remarketed.” In 2007, about 10 million used vehicles were sold at more than 400 auctions in the United States. Large consigners face decisions every day about when, where, and at what price to offer these vehicles, which has significant financial implications for their profitability. To address the challenges of the distribution process, Power Information Network (PIN), a division of J.D. Power and Associates, developed the PIN Optimal Distribution of Auction Vehicles System (ODAV), an automated decision optimization system that helps remarketers maximize profits through the most advantageous distribution of their auction vehicles. At the core of the system is a combination of three models that determine the distribution of the vehicles on a daily basis: a nearest neighbor linear regression model for short-term auction price forecasting; an autoregressive integrated moving average time-series analysis model for volume-price elasticity; and a genetic algorithm optimizer for vehicle distribution. Since its launch in 2003, PIN has been providing ODAV services on a daily basis, and to date, more than two million vehicles have been distributed through this system. In this paper, we will describe the PIN ODAV System, its implementation, and the business impact by using as an example the experience with our largest client, Chrysler Group LLC.

A variable annuity is a popular product for investing retirement income. However, thousands of similar-looking variable annuity products are being offered by hundreds of financial service companies. In such a scenario, how can Prudential achieve meaningful product differentiation to increase the sales of its variable annuities? The solution led to the development and implementation of the “Emotion Quotient” (EQ) Tool. The EQ Tool enabled Prudential to redefine its marketing and sales approach along a proactive (as opposed to responsive) market orientation paradigm. This was accomplished by first using the EQ Tool to uncover and quantify the prevalence of certain emotions (such as fear and regret) in the prospective consumer and then pitching relevant variable annuity product(s) that could mitigate the specific behavioral risk corresponding to the prevalent emotion(s). This approach, which was backed by extensive research (as described in this study), enabled Prudential to gain over $450 million lift in variable annuity sales and contributed to consumer welfare by promoting awareness of behavioral risk to investors who are within five years of their retirement. This research study illustrates how industry can collaborate with academia to successfully apply marketing science to solve real-world business problems.

We develop a robust model for estimating, tracking, and managing brand equity for multicategory brands based on customer survey and financial measures. This model has two components: (1) offering value (computed from discounted cash flow analysis) and (2) relative brand importance (computed from brand choice models such as multinomial logit, heteroscedastic extreme value, and mixed logit). We apply this model to estimate the brand equity of Allstate—a leading insurance company—and its leading competitor, which compete in multiple categories. The model captures the brand's spillover effects from one category to another. In addition, we identify the dimensions that drive a brand's image, examine the relationships among advertising, brand equity, and shareholder value, and build a decision support simulator for the focal brand. Our model provides reliable estimates of brand equity, and our results show that advertising has a strong long-term positive influence on brand equity, which is significantly positively related to shareholder value. The model, the brand equity estimates, and the decision support simulator are used by key executives across multiple functional areas and have enabled the company to substantially gain by reallocating its advertising resources to improve brand equity and shareholder value, and by offering better guidance to analysts and investors.

No abstract available.

A call for funded proposals that was jointly sponsored by the Wharton Interactive Media Initiative (http://www.whartoninteractive.com) and the Marketing Science Institute (http:// www.msi.org) on UGC demonstrated a strong interest in a variety of research approaches (e.g., experimental, analytical theory, empirical structural, statistical, and data mining) that are being used to study the creation of and impact of UGC. Marketing Science strongly supports this area as important to our field—hence, this call for papers for a special issue. Marketing Science is looking for innovative and groundbreaking papers that address issues related to UGC. Examples of paper topics might include the following

This editorial introduces the special issue on marketing science and health. We begin by describing the healthcare ecosystem and its many distinguishing features relative to other markets. With its large share of U.S. and world gross domestic product; rapid changes on the demand, supply, and regulatory sides; and a complex ecosystem with many types of participants, healthcare markets provide a rich canvas of novel research opportunities for marketing scholars. We then describe the special issue process and the papers published in the special issue. We summarize key themes that emerge from these papers and conclude with a discussion of future research opportunities in the area.

This paper develops a new rationale for decentralization in distribution channels: providing a one-stop comparison shopping experience for consumers. In our duopoly model, when consumers are knowledgeable about their brand preferences, each manufacturer would distribute through its own vertically integrated retail outlets only. When some consumers are unsure about their brand preferences, however, it may be optimal for one of the manufacturers to also distribute through its competitor’s outlets. The resulting equilibrium has several interesting properties. First, only one of the manufacturers chooses to add competitor-outlet distribution, not both—even when the manufacturers are symmetric. Second, the manufacturer distributing through its competitor’s outlets also distributes through its own outlets, i.e., its distribution strategy is a hybrid strategy, combining vertical integration and decentralization. Third, when the manufacturers’ brands are asymmetric, it is the weaker brand that has a stronger incentive to pursue hybrid distribution. Fourth, the competitor’s outlets in question welcome the new brand, even when no consumer would actually buy the new brand—a case of pure showrooming. These results highlight the linkages between distribution strategy, shopping efficiency, and retail formats. Shopping costs and consumers’ uncertainty about their own brand preferences create a demand for multibrand retailing, and in pursuing this demand, manufacturers may eschew the efficiency advantages of vertical integration in favor of hybrid distribution. However, the fact that only one of the manufacturers chooses to do so suggests that this strategy also has weaknesses, which we discuss in the paper.

This paper reports on the development and implementation of a large-scale, marketing analytics framework for improving the segmentation, targeting and optimization of a consumer-facing firm’s marketing activities. The framework leverages detailed transaction data of the type increasingly becoming available in such industries. The models are customized to facilitate casino operations and implemented at the MGM Resorts International’s group of companies. The core of the framework consists of empirical models of consumer casino visitation and play behavior and its relationship to targeted marketing effort. Important aspects of the models include incorporation of rich dimensions of heterogeneity in consumer response, accommodation of state-dependence in consumer behavior, as well as controls for the endogeneity of targeted marketing in inference, all issues that are salient in modern empirical marketing research. The paper discusses details of the models as well as practical issues involved in translating econometric models of this sort into implementable solutions in the field. A novel aspect of the paper is an analysis of a randomized trial implemented at the firm involving about 2M consumers comparing the performance of the proposed marketing-science based models to the existing status quo. We find the impact of the solution is to produce about $1M to $5M incremental profits per campaign, and about an 8% improvement in the Return on Investment of marketing dollars. At current levels of marketing spending, this translates to between $10M and $15M in incremental annual profit in this setting. More generally, we believe the results showcase the value of combining large, disaggregate, individual-level datasets with marketing analytics solutions for improving outcomes for firms in real-world settings. We hope our demonstrated improvement from analytics adoption help accelerate faster diffusion of marketing science into practice.

Whereas the extant literature on entry-order effects establishes that first entrants often earn higher market shares (“market-share advantage”), the literature on distribution suggests that increased distribution has a positive effect on sales. Can distribution help us better understand entry-order effects on market shares? This paper examines how the first entrant in a geographical market achieves a market-share advantage through distribution. For this purpose, I propose a simple method of decomposing sales into physical distribution and sales performance. The data come from a manually collected panel on six major Japanese convenience-store chains from 47 geographical markets between 1991 and 2007. Using an instrumental variable approach to address the potential endogeneity of entry order, I find first entrants have a positive market-share advantage over later entrants. Specifically, the physical distribution, measured by the number of outlets in a market, drives most of the advantage. Meanwhile, the positive effect on sales performance for the first chain brand becomes nonexistent when I control for the outlet density. This paper further finds that the density of own outlets is nonmonotonically (inverted U) related to sales performance per outlet, suggesting dynamic outlet expansion faces a trade-off between the business-stealing effect in a chain (“cannibalization”) and the advertising effect through repetition. Data and the online appendix are available at https://doi.org/10.1287/mksc.2017.1029 .

This paper studies the ability of competing retailers to form a cartel by sharing information with their mutual manufacturer. In a market characterized by demand uncertainty, colluding retailers desire to share information about the potential market demand in order to coordinate on the optimal collusive retail price. However, since direct information-sharing between competing firms is considered to be a possible signal for collusion, according to the antitrust laws, the retailers search for a mechanism to exchange information in a manner that would not raise the suspicions of the antitrust authorities. This paper examines such a mechanism: each retailer shares his private information with the mutual manufacturer and uses the wholesale price to infer the market condition and coordinate on the cartel price. Although a cartel at the retail level limits the manufacturer’'s sold quantity, under certain conditions, the manufacturer is better-off accepting the retailers' ’private information, thereby facilitating the cartel formation. Moreover, a situation in which the retailers cannot collude by sharing information horizontally and they collude by sharing information with the manufacturer can result in a lower consumer surplus.

In this paper, we propose an automated and scalable garment recommender system using real-time in-store videos that can improve the experiences of garment shoppers and increase product sales. The video-based automated recommender (VAR) system is based on observations that garment shoppers tend to try on garments and evaluate themselves in front of store mirrors. Combining state-of-the-art computer vision techniques with marketing models of consumer preferences, the system automatically identifies shoppers’ preferences based on their reactions and uses that information to make meaningful personalized recommendations. First, the system uses a camera to capture a shopper’s behavior in front of the mirror to make inferences about her preferences based on her facial expressions and the part of the garment she is examining at each time point. Second, the system identifies shoppers with preferences similar to the focal customer from a database of shoppers whose preferences, purchasing, and/or consideration decisions are known. Finally, recommendations are made to the focal customer based on the preferences, purchasing, and/or consideration decisions of these like-minded shoppers. Each of the three steps can be implemented with several variations, and a retailing chain can choose the specific configuration that best serves its purpose. In this paper, we present an empirical test that compares one specific type of VAR system implementation against two alternative, nonautomated personal recommender systems: self-explicated conjoint (SEC) and self-evaluation after try-on (SET). The results show that VAR consistently outperforms SEC and SET. A second empirical study demonstrates the feasibility of VAR in real-time applications. Participants in the second study enjoyed the VAR experience, and almost all of them tried on the recommended garments. VAR should prove to be a valuable tool for both garment retailers and shoppers. Data, as supplemental material, are available at http://dx.doi.org/10.1287/mksc.2016.0984 .

Customer privacy is increasingly important to marketers. High-profile breaches of databases containing sensitive customer information, and the growing need to build the infrastructure required to support analysis of big data, present nontrivial obstacles to researchers seeking individual-level customer data from firms. In this paper, we show that recent developments in machine learning may enable firms to transfer a generative model, instead of data, thus potentially obviating the process of anonymizing and sampling customer data for release, for use in a variety of analytic use cases. We demonstrate the efficacy of a specific deep learning model, Generative Adversarial Networks (GANs), in preserving desired characteristics of original data. In real-world settings, we find that GANs can double the accuracy as compared to the best benchmark methods. We also demonstrate that GANs can be used to solve marketing problems of price markups for optimal profits and customer targeting, and that a single GAN can tackle multiple marketing problems. Furthermore, GANs have volume and velocity advantages, as the size of informational transfer grows according to model complexity, and it can readily handle real-time data streams.

Sellers may display unreasonably high prices (in high-cost oriented contexts) that are never accepted or would surely be discounted through bilateral bargaining. Conversely, general or vague prices with incredible appeals may be advertised (in low-cost oriented settings) as a range or for a category but not tied to specific items. Nevertheless, these seemingly irrelevant or unbinding prices can affect buyer behavior and bargaining outcome. This paper presents a new explanation for these puzzling phenomena. We propose that advertised reference prices can be a strategic tool to communicate privately known seller costs to influence optimal buyer strategy to search value information. We show that cheap-talk communication via uncommitted prices can be endogenously credible, because optimal buyer search strategy can be imperfectly aligned with seller preference. In particular, a high-cost seller may prefer the buyer to acquire information in a more cautious manner (i.e., less willing to stop at good news but more eager to quit at bad news) than a low-cost seller, which may coincide with the buyer's optimal search strategy. We demonstrate that endogenous buyer search can serve as a two-way discipline to regulate both high- and low-cost sellers' incentive for deception, which thus can sustain credible communication for high-cost and/or low-cost oriented settings.

This paper investigates a contest in information revelation between firms that seek to persuade consumers by revealing positive own information and negative information about the rival. In the face of limited bandwidth, firms are forced to make a trade-off between disclosing their own positive information and their rival’s negative information. A negative-communication equilibrium, in which firms disclose rival’s negative information whenever possible, exists when consumers have poor outside options or when firms are better informed. Bandwidth limitations make competitive firms more likely to disclose information compared to when they have no limitations. When firms strictly prefer consumers to choose the outside option over the rival (as in political contests), there is a greater prevalence of the negative communication equilibrium while the incidence of positive communication is lowered. Finally, when firms are asymmetric in their ex-ante quality valuations, the higher quality firm is less likely to engage in negative communication.

The underlying channels through which peer influence operates in durable good adoption can affect the ability of marketers to leverage them. In this paper, we assess whether the visibility of peers' adoption decisions leads to greater peer influence. The context we study is residential rooftop solar panels. We exploit the plausibly exogenous location and orientation of peers' rooftop solar panels relative to proximate roadways and visual obstructions, such as vegetation, in order to determine whether geographically proximate peer installations increase a household's probability of solar adoption more if they are visible from the road. Highlighting the role of peer influence at the very local level, we find evidence of peer influence for non-visible solar arrays only within 100m on the same street. We also demonstrate that installations that are visible from the street exert peer influence at distances of at least 500m. A peer installation within 500m that is visible from proximate roadways at angles totaling 90 degrees exerts the same magnitude peer effect as a non-visible installation within 100m. The effect of peer visibility is moderated by the economic value the peers receive from installing solar, providing suggestive evidence of social learning through visual information.

"Network adequacy regulations" expand patients' access to hospitals by mandating a lower bound on the number of hospitals that health insurers must include in their networks. Such regulations, however, compromise insurers' bargaining position with hospitals, which may increase hospital reimbursement rates, and may consequently be passed through to consumers in the form of higher premiums. In this paper, I quantify this effect by developing a model that endogenously captures: (i) how insurers form hospital-networks, (ii) how they bargain with hospitals over rates by threatening to drop them out of network or to replace them with an out of network hospital, and (iii) how they set premiums in an imperfectly competitive market. I estimate this model using detailed data from a Massachusetts health insurance market, and I simulate the effects of a range of regulations. I find that "tighter" regulations, which force insurers to include more than 85% of the hospital-systems in the market, raise the average reimbursement rates paid by some insurers by at least 28%. More moderate regulations, however, can expand the hospital networks without leading to large hikes in reimbursement-rates.

The interest in social networks among marketing scholars and practitioners has sharply increased in the last decade. One social network of which network scholars increasingly recognize the unique value is the academic collaboration (coauthor) network. We offer a comprehensive database of the collaboration network among marketing scholars over the last 40 years (available at http://mktsci.pubs.informs.org ). Based on the ProQuest database, it documents the social collaboration among researchers in dozens of the leading marketing journals, enabling us to create networks of active marketing researchers. Unlike most of the published academic collaboration research, our database is dynamic and follows the evolution of the field over many years. In this paper, we describe the database and point to some basic network descriptives that lead to interesting research questions. We believe this database can be of much value to researchers interested in the evolution of social networks over time, as well as the specific evolution of the marketing discipline. The data set described in this paper is maintained by the authors and available through http://mktsci.pubs.informs.org

The existing marketing literature suggests that persuasive advertising elicits counteractions from competing manufacturers and consequently leads to wasteful cancellation of the advertising effects. Thus, persuasive advertising is widely perceived to be combative in nature. A series of previously published papers demonstrates that appropriate targeting may partially mitigate the combative nature of persuasive advertising in that either the rival manufacturer or the retailer may benefit. In this paper, we complement their results by demonstrating the possibility that every channel member may benefit from persuasive advertising, i.e., a Pareto improvement along the distribution channel, thereby leading to the conclusion that persuasive advertising need not result in channel conflict.