Latest Articles Include:
- Editorial--Marketing Science and the Financial Crisis
- Marketing Science 28(2):201 (2009)
No abstract available. - Website Morphing
- Marketing Science 28(2):202-223 (2009)
Virtual advisors often increase sales for those customers who find such online advice to be convenient and helpful. However, other customers take a more active role in their purchase decisions and prefer more detailed data. In general, we expect that websites are more preferred and increase sales if their characteristics (e.g., more detailed data) match customers' cognitive styles (e.g., more analytic). "Morphing" involves automatically matching the basic "look and feel" of a website, not just the content, to cognitive styles. We infer cognitive styles from clickstream data with Bayesian updating. We then balance exploration (learning how morphing affects purchase probabilities) with exploitation (maximizing short-term sales) by solving a dynamic program (partially observable Markov decision process). The solution is made feasible in real time with expected Gittins indices. We apply the Bayesian updating and dynamic programming to an experimental BT Group (formerly Bri! tish Telecom) website using data from 835 priming respondents. If we had perfect information on cognitive styles, the optimal "morph" assignments would increase purchase intentions by 21%. When cognitive styles are partially observable, dynamic programming does almost as well--purchase intentions can increase by almost 20%. If implemented system-wide, such increases represent approximately $80 million in additional revenue. - Commentary--Discussion of "Website Morphing"
- Marketing Science 28(2):224 (2009)
Website morphing seems to be a useful technique, with applications beyond matching cognitive style. - Commentary--Discussion on "Website Morphing" by Hauser, Urban, Liberali, and Braun
- Marketing Science 28(2):225 (2009)
These comments are a tribute to an impressive paper and suggestions for clarification of some fairly minor issues. - Commentary--Discussion of the Article "Website Morphing"
- Marketing Science 28(2):226 (2009)
The article under discussion illustrates the trade-off between optimization and exploration that is fundamental to statistical experimental design. In this discussion, I suggest that the research under discussion could be made even more effective by checking the fit of the model by comparing observed data to replicated data sets simulated from the fitted model. - Rejoinder--Response to Comments on "Website Morphing"
- Marketing Science 28(2):227-228 (2009)
Website morphing draws on the Expected Gittins' solution to a partially observable Markov process, on the rapid consumer-segment updating with Bayesian methods, and on matching a website's look and feel to a visitor's cognitive style. In each area there are exciting research opportunities including optimality in the presence of switching costs (within a visit), Bayesian updating of cognitive styles across websites, extensions to other segmentation schemes such as cultural styles, morphing of other website characteristics such as advertising, and applications to other media such as smartphones. - Slippage in Rebate Programs and Present-Biased Preferences
- Marketing Science 28(2):229-238 (2009)
Present-biased preferences capture the idea that individuals may find immediate payoffs significantly more salient than any future payoffs, rather than simply discounting the future in a time-consistent manner. In this paper we show that consumers' present-biased preferences can generate slippage, and we explore whether this can explain firms' use of mail-in rebates. We assume that the consumer population comprises members who have various degrees of present bias. The model demonstrates that if consumers have homogeneous willingness to pay for a product (and thus rebates do not serve as a mechanism for traditional price discrimination) rebates may still profitably exploit slippage, but to do so they must generate very high slippage rates. This is, because the rebate must greatly exceed the price markup because the rebate must compensate consumers for the cost of redemption and the delay in receiving the rebate. The ability of rebate programs to take advantage of presen! t-biased consumers is quite limited in settings where there is significant variance in the degree of present bias within the population unless the extent of consumers' present bias is highly correlated with their rebate redemption costs. - Movie Advertising and the Stock Market Valuation of Studios: A Case of "Great Expectations?"
- Marketing Science 28(2):239-250 (2009)
Product innovation is the key revenue driver in the motion picture industry. Because major studios typically launch fewer than 20 movies per year, the financial performance of a single release can have a major effect on the studio's profitability. In this paper we study how single movie releases impact the investor valuation of the studio. We analyze the change in postlaunch stock price and predict the direction and magnitude of excess returns based on the revenue expectation built up for a movie release. That expectation is set, in part, by media support; i.e., highly advertised movies are expected to draw larger audiences than others. By using an event-study methodology, we isolate the impact of a movie launch on studio stock price and track the determinants of that change. We examine a comprehensive data set comprising over 300 movies released by the largest studios. Our results indicate a clear interaction between the marketing support received by a movie and the ! direction and magnitude of its excess stock return post launch. Movies with above average prelaunch advertising have lower postlaunch stock returns than films with below average advertising. Our findings also suggest that movies that are hits at the box office may result in a lowering of stock price if they had high media support because of high performance expectations built up prior to launch. Thus prelaunch advertising plays a dual role of informing consumers about a movie's arrival as well as helping investors form expectations about the studio's profit performance. - Real-Time Evaluation of E-mail Campaign Performance
- Marketing Science 28(2):251-263 (2009)
We develop a testing methodology that can be used to predict the performance of e-mail marketing campaigns in real time. We propose a split-hazard model that makes use of a time transformation (a concept we call virtual time) to allow for the estimation of straightforward parametric hazard functions and generate early predictions of an individual campaign's performance (as measured by open and click propensities). We apply this pretesting methodology to 25 e-mail campaigns and find that the method is able to produce in an hour and fifteen minutes estimates that are more accurate and more reliable than those that the traditional method (doubling time) produces after 14 hours. Other benefits of our method are that we make testing independent of the time of day and we produce meaningful confidence intervals. Thus, our methodology can be used not only for testing purposes, but also for live monitoring. The testing procedure is coupled with a formal decision theoretic frame! work to generate a sequential testing procedure useful for the real time evaluation of campaigns. - Optimal Bundling Strategies in Multiobject Auctions of Complements or Substitutes
- Marketing Science 28(2):264-273 (2009)
We consider a problem at the interface of auctions and bundling. Our revenue-maximizing seller seeking to auction one unit each of two complements or substitutes in the best-of-three formats: the auction of the bundle, separate auctions of the individual items, and a combinatorial auction. We draw on an analytical model to address the following questions: (i) Which of the auctioning strategies is optimal under the second-price, sealed-bid format? (ii) What is the optimal strategy for the bidders? (iii) When the objects are asymmetrically valued (e.g., Super Bowl ticket versus souvenir), what is the optimal auctioning sequence under the pure components strategy? Our results suggest that separate auctions of the two objects are superior to the auction of the bundle for most substitutes and even moderate complements when there are at least four bidders. The auction of the pure bundle is better suited for strong complements or with too few bidders. When the combinatorial a! uction is an available option, it weakly dominates the auction of the pure bundle but has domains of inferiority relative to the separate auctions. When the objects are asymmetric in value, it is optimal to auction the higher-valued object first. - Zooming In: Self-Emergence of Movements in New Product Growth
- Marketing Science 28(2):274-292 (2009)
In this paper, we propose an individual-level approach to diffusion and growth models. By zooming in, we refer to the unit of analysis, which is a single consumer (instead of segments or markets) and the use of granular sales data (daily) instead of smoothed (e.g., annual) data as is more commonly used in the literature. By analyzing the high volatility of daily data, we show how changes in sales patterns can self-emerge as a direct consequence of the stochastic nature of the process. Our contention is that the fluctuations observed in more granular data are not noise, but rather consist of accurate measurement and contain valuable information. By stepping into the noise-like data and treating it as information, we generated better short-term predictions even at very early stages of the penetration process. Using a Kalman-Filter-based tracker, we demonstrate how movements can be traced and how predictions can be significantly improved. We propose that for such tasks, d! aily data with high volatility offer more insights than do smoothed annual data. - Click Fraud
- Marketing Science 28(2):293-308 (2009)
Click fraud is the practice of deceptively clicking on search ads with the intention of either increasing third-party website revenues or exhausting an advertiser's budget. Search advertisers are forced to trust that search engines detect and prevent click fraud even though the engines get paid for every undetected fraudulent click. We find conditions under which it is in a search engine's interest to allow some click fraud. Under full information in a second-price auction, if x% of clicks are fraudulent, advertisers will lower their bids by x%, leaving the auction outcome and search engine revenues unchanged. However, if we allow for uncertainty in the amount of click fraud or change the auction type to include a click-through component, search engine revenues may rise or fall with click fraud. A decrease occurs when the keyword auction is relatively competitive because advertisers lower their budgets to hedge against downside risk. If the keyword auction is less com! petitive, click fraud may transfer surplus from the winning advertiser to the search engine. Our results suggest that the search advertising industry would benefit from using a neutral third party to audit search engines' click fraud detection algorithms. - Strategic Assortment Reduction by a Dominant Retailer
- Marketing Science 28(2):309-319 (2009)
In certain product categories, large discount retailers are known to offer shallower assortments than traditional retailers. In this paper, we investigate the competitive incentives for such assortment decisions and the implications for manufacturers' distribution strategies. Our results show that if one retailer has the channel power to determine its assortment first, then it can strategically reduce its assortment by carrying only the popular variety while simultaneously inducing the rival retailer to carry both the specialty and popular varieties. The rival retailer then bears higher assortment costs, which leads to relaxed price competition for the commonly carried popular variety. We also show that when the manufacturer has relative channel power, it chooses alternatively to distribute both product varieties through both retailers. Our analysis suggests, therefore, that when a retailer becomes dominant in the distribution channel, it facilitates retail segmentatio! n into discount shops, carrying limited product lines, and specialty shops carrying wider assortments. We also illustrate how retailer power leading to strategic assortment reduction can lead to lower consumer surplus. - Path Data in Marketing: An Integrative Framework and Prospectus for Model Building
- Marketing Science 28(2):320-335 (2009)
Many data sets, from different and seemingly unrelated marketing domains, all involve paths--records of consumers' movements in a spatial configuration. Path data contain valuable information for marketing researchers because they describe how consumers interact with their environment and make dynamic choices. As data collection technologies improve and researchers continue to ask deeper questions about consumers' motivations and behaviors, path data sets will become more common and will play a more central role in marketing research. To guide future research in this area, we review the previous literature, propose a formal definition of a path (in a marketing context), and derive a unifying framework that allows us to classify different kinds of paths. We identify and discuss two primary dimensions (characteristics of the spatial configuration and the agent) as well as six underlying subdimensions. Based on this framework, we cover a range of important operational is! sues that should be taken into account as researchers begin to build formal models of path-related phenomena. We close with a brief look into the future of path-based models, and a call for researchers to address some of these emerging issues. - Limited Edition Products: When and When Not to Offer Them
- Marketing Science 28(2):336-355 (2009)
Many brands today introduce limited edition (LE) products as part of their product line. However, little is known about the conditions under which a brand should introduce an LE product or the competitive implications of doing so. We investigate this issue using a game theoretic model of a market where two brands compete for consumers who desire exclusivity. Our analysis shows that adding an LE product has a positive direct effect on brand profits through the increased willingness of consumers to pay for such a product, but also has a negative strategic effect by increasing price competition between brands. These effects result in different conclusions depending on the nature of brand differentiation. When brands differ in quality, we show that only the high-quality brand may gain in comparison to a scenario where there are no LE products. Although a low-quality brand may offer an LE product as a defensive strategy, its profits are lower than would be in a world withou! t LE products because of the negative strategic effect. When we consider brands that are differentiated on a horizontal attribute such as taste, we find that the negative strategic effects cause lower equilibrium profits if both brands introduce LE products. Yet brands cannot avoid introducing LE products because they face a prisoners' dilemma. - Estimating Demand Heterogeneity Using Aggregated Data: An Application to the Frozen Pizza Category
- Marketing Science 28(2):356-372 (2009)
This paper combines different aggregate-level data sets to identify new product demand in consumer packaged goods (CPG) categories. Our approach augments market-level time-series data with widely available summaries of household purchase behavior, i.e., brand penetration and purchase set size data. We show that this augmentation is helpful in the estimation of consumer heterogeneity. For instance, observing a brand with relatively large shares and low penetration typically indicates that preferences are dispersed, with relatively few customers liking the brand a lot. Whereas the combination of share and penetration is informative about heterogeneity with realistic sample sizes, in isolation neither variable may lead to precise estimates of heterogeneity. In addition, other widely available data, e.g., category penetration, is helpful in estimating the size of the total market. Using a large Monte Carlo study, the paper demonstrates the benefits of the proposed approach! in estimating model parameters, price elasticities, and brand switching. Empirically, the approach is used to evaluate the launch of a new national brand, DiGiorno, in the frozen pizza category. The new brand is inferred to be very successful at expanding the category, while avoiding cannibalization of existing company share. Using only standard information, i.e., market shares, to estimate the demand model leads, in our data, to poor estimates of the degree of consumer taste variation and of switching to a new brand. - Market Research and Innovation Strategy in a Duopoly
- Marketing Science 28(2):373-396 (2009)
We model a duopoly in which ex ante identical firms must decide where to direct their innovation efforts. The firms face market uncertainty about consumers' preferences for innovation on two product attributes and technology uncertainty about the success of their research and development (R&D) investments. Firms can conduct costly market research before setting R&D strategy. We find that the value of market information to a firm depends on whether its rival is expected to obtain this information in equilibrium. Consequently, one firm may forgo market research even though its rival conducts such research and learns the true state of demand. We examine both vertical and horizontal demand structures. With vertical preferences, firms are a priori uncertain about which attribute all consumers will value more. In this case, a firm that conducts market research always attempts innovation on the attribute it discovers that consumers prefer and expends more on R&D than a rival ! that has not conducted market research. With horizontal preferences, distinct segments exist--each caring about innovation on only one attribute--and firms are a priori uncertain how many consumers each segment contains. In this case, a firm that conducts market research may follow a niche strategy and attempt innovation to serve the smaller segment to avoid intense price competition for the larger segment. A firm that conducts market research may therefore invest less in R&D and earn lower postlaunch profits than a rival that has forgone such research. - Focus on Authors
- Marketing Science 28(2):397-401 (2009)
No abstract available.
No comments:
Post a Comment