Explore the vast range of titles available.

There is substantial academic interest in modeling consumer experiential learning. However, (approximately) optimal solutions to forward-looking experiential learning problems are complex, limiting their behavioral plausibility and empirical feasibility. We propose that consumers use cognitively simple heuristic strategies. We explore one viable heuristic—index strategies—and demonstrate that they are intuitive, tractable, and plausible. Index strategies are much simpler for consumers to use but provide close-to-optimal utility. They also avoid exponential growth in computational complexity, enabling researchers to study learning models in more complex situations. Well-defined index strategies depend on a structural property called indexability. We prove the indexability of a canonical forward-looking experiential learning model in which consumers learn brand quality while facing random utility shocks. Following an index strategy, consumers develop an index for each brand separately and choose the brand with the highest index. Using synthetic data, we demonstrate that an index strategy achieves nearly optimal utility at substantially lower computational costs. Using IRI data for diapers, we find that an index strategy performs as well as an approximately optimal solution and better than myopic learning. We extend the analysis to incorporate risk aversion, other cognitively simple heuristics, heterogeneous foresight, and an alternative specification of brands.

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 .

Choice-based conjoint (CBC) studies have begun to rely on simulators to forecast equilibrium prices for pricing, strategic product positioning, and patent/copyright valuations. Whereas CBC research has long focused on the accuracy of estimated relative partworths of attribute levels, predicted equilibrium prices and strategic positioning are surprisingly and dramatically dependent on scale: the magnitude of the partworths (including the price coefficient) relative to the magnitude of the error term. Although the impact of scale on the ability to estimate heterogeneous partworths is well known, neither the literature nor current practice address the sensitivity of pricing and positioning to scale. This sensitivity is important because (estimated) scale depends on seemingly innocuous market-research decisions such as whether attributes are described by text or by realistic images. We demonstrate the strategic implications of scale using a stylized model in which heterogeneity is modeled explicitly. If a firm shirks on the quality of a CBC study and acts on incorrectly observed scale, a follower, but not an innovator, can make costly strategic errors. Externally valid estimates of scale are extremely important. We demonstrate empirically that image realism and incentive alignment affect scale sufficiently to change strategic decisions and affect patent/copyright valuations by hundreds of millions of dollars.

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. Firms traditionally rely on interviews and focus groups to identify customer needs for marketing strategy and product development. User-generated content (UGC) is a promising alternative source for identifying customer needs. However, established methods are neither efficient nor effective for large UGC corpora because much content is noninformative or repetitive. We propose a machine-learning approach to facilitate qualitative analysis by selecting content for efficient review. We use a convolutional neural network to filter out noninformative content and cluster dense sentence embeddings to avoid sampling repetitive content. We further address two key questions: Are UGC-based customer needs comparable to interview-based customer needs? Do the machine-learning methods improve customer-need identification? These comparisons are enabled by a custom data set of customer needs for oral care products identified by professional analysts using industry-standard experiential interviews. The analysts also coded 12,000 UGC sentences to identify which previously identified customer needs and/or new customer needs were articulated in each sentence. We show that (1) UGC is at least as valuable as a source of customer needs for product development, likely more valuable, compared with conventional methods, and (2) machine-learning methods improve efficiency of identifying customer needs from UGC (unique customer needs per unit of professional services cost). Data are available at https://doi.org/10.1287/mksc.2018.1123 .

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 British 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.

Deep learning is delivering impressive results in AI applications. Apple's Siri, for example, translates the human voice into computer commands that allow iPhone owners to get answers to questions, send messages, and navigate their way to and from obscure locations. Automated driving enables people today to go hands-free on expressways, and it will eventually do the same on city streets. In biology, researchers are creating new molecules for DNA-based pharmaceuticals. The technology that underpins deep learning is becoming increasingly capable of analyzing big databases for patterns and insights. It isn't difficult to imagine a day when companies will be able to integrate a wide array of databases to discern what consumers want with greater sophistication and analytic power and then leverage that information for market advantage. To compare deep learning with traditional methods for marketing analytics, we studied a large database of click-streams, demographics, and ad exposures relating to the credit card market from NerdWallet, a large online vendor of credit cards, based in San Francisco.

The authors test methods, based on cognitively simple decision rules, that predict which products consumers select for their consideration sets. Drawing on qualitative research, the authors propose disjunctions-of-conjunctions (DOC) decision rules that generalize well-studied decision models, such as disjunctive, conjunctive, lexicographic, and subset conjunctive rules. They propose two machine-learning methods to estimate cognitively simple DOC rules. They observe consumers' consideration sets for global positioning systems for both calibration and validation data. They compare the proposed methods with both machine-learning and hierarchical Bayes methods, each based on five extant compensatory and noncompensatory rules. For the validation data, the cognitively simple DOC-based methods predict better than the ten benchmark methods on an information theoretic measure and on hit rates. The results are robust with respect to format by which consideration is measured, sample, and presentation of profiles. The article closes with an illustration of how DOC-based rules can affect managerial decisions.