Search

One of the major demand related risks for companies that produce consumer electronics goods is change in consumer preferences over time as reflected in the weights they attach to the attributes of products. This contributes to the difficulty of predicting whether consumers will purchase a new product or not and the accuracy of such forecasts can have significant ramifications for companies’ strategies, profitability and even their chances of survival. Knowledge of attribute-weights and accurate forecasts of new products can give companies better insights during the product development stages, inform go-no-go decisions on whether to launch a developed product and also support decisions on whether a recently launched product should be withdrawn or not due to poor early stage sales. Despite the important implications of change in attribute-weights, no research has investigated the extent to which such changes occur and impact on the accuracy of forecasts of the future market share of these products. Prior to the current research, it was assumed that the weights are constant over time – even when the nature of the attributes was assumed to change. To investigate these concerns choice based conjoint (CBC) was applied to data gathered in a longitudinal survey of consumer choices relating a range of consumer electronic products, where innovation has different rates and the product life cycles are various. This allowed an assessment of the extent to which the weights of attributes of choice-based conjoint models change over a six months period for consumer durable products and the degree to which this variability is dependent on the nature of the product. It demonstrates that the change in weights is greater for products that have high technological complexity and shorter lifecycles and also links the changeability of weights to the characteristics of potential consumers. The results of thesis demonstrate that the assumption of constant weights can potentially lead to inaccurate market share forecast for high-tech, short life-cycle products that are launched several months after the choice-based modelling has been conducted.

This dissertation is a collection of five essays examining different aspects of consumer and firm behavior in dynamic markets. The first essay combines clickstreams of users at a major news website with Facebook activity data, to study if social networks complement or compete for online browsing time. This is the first empirical study to show that Facebook activity increases time spent on news sites. Online news consumption is a shared experience, as the activity of social network friends strongly influences the behavior of other network members. We also find that visitors’ own browsing patterns are important predictors of online content consumption. The second essay examines consumer attitudes to risk and uncertainty vis-a-vis their purchase and search decisions for air tickets online. Using a two-stage model of purchase incidence and carrier choice, we find that browsing experience, search costs and product characteristics are important predictors of purchase incidence. Implications for website managers are also discussed. The third essay provides insights on the impact of customer heterogeneity and preference stochasticity on behavior based price discrimination. While customer heterogeneity intensifies competition, resulting in greater price discrimination, preference stochasticity reduces the incidence of price discrimination. Overall, the effect of preference stochasticity is more salient. The fourth essay presents models of strategic interaction to analyze the impact of dominance and concentration on pricing strategies. We show that lack of market dominance is a sufficient condition for discounts to existing customers. We further test our predictions via an experiment with pricing professionals. The behavior of professionals confirms that price discrimination increases with market dominance and concentration; however, lack of dominance is not a sufficient condition for loyalty discounts. We contend that increasing competition is a more effective means of improving consumer welfare compared to regulating dominant firms. The fifth essay considers the role of identity and customer type recognition in influencing pricing behavior in dynamic markets with symmetric and asymmetric players. When customer identity is detectable firms charge higher prices to repeat customers while new customers are offered lower prices. However, pricing behavior changes when information on customer type is available and this behavior varies with market structure. Age, education and experience of managers are also found to significantly influence pricing behavior.

My dissertation explores how firms can use individual longitudinal choice data to increase usage and spending in experiential goods categories, specifically in two different live events domains: art performances and sports events. In the first essay, I study how consumers choose customizable bundles of art performances while balancing preferences for the constituent items and within-bundle variety. Known as the diversification effect, consumers prefer higher levels of variety when making choices for multiple consumption occasions. This suggests that picking the right level of variety is a crucial part of art performance bundle choices. While customizability adds flexibility to consumers’ choices, due to the large number of possible bundles, it could increase consumers’ cognitive costs. Based on the proposed model, I make individualized recommendations that reflect heterogeneous preferences for not only the performances but also for the level of variety. To model consumers’ choices of art performance bundles, it is necessary to 1) characterize the performances, 2) define and measure the variety of prospective bundles, and 3) devise an efficient way of estimating bundle choices in the prohibitively large combinatorial space of possible bundles. Using natural language processing, I extract latent dimensions of the art performances that can be used to characterize the performances. I use these latent attributes to construct variety metrics that capture consumers’ perception of bundle-level variety. Additionally, I devise a novel Monte Carlo approach to integrate over the space of unobserved order in which the bundle was assembled to tame the curse-of-dimensionality in the estimation process. I find that including variety metrics substantially improves predictive performance of the model, allowing the performing arts organization to make better individualized recommendations. In the second essay, I study the cross-channel structure of the National Football League (NFL) ticket markets and consumers’ purchase channel choices with the goal of devising optimal dynamic pricing and inventory policies across different channels. Professional sports teams have widely adopted dynamic pricing policy, which resulted in significant revenue improvements. At the same time, the growth of legal secondary markets has contributed to the development of a complex market structure with multiple channels. Understanding the cross-channel structure and consumers’ channel choice process allows teams to make more informed pricing and inventory decisions. Partnering with an anonymous NFL team, I collected time-series data on the availability and pricing of tickets on primary and three major secondary channels and combine it with transaction data. I propose a three-part model to understand the supply and demand dynamics: sellers’ supply decision, buyers’ purchase decision, and channel choice to capture the evolution of the choice environment where ticket availability and prices vary over time and channels. I find that there exist significant price differences across channels even after controlling for seat quality, and that channel choices reveal differential price sensitivities, effects of time-until-game across channels, and strong past dependence. Importantly, the investigation into row-level supply decisions reveal potential cross-channel effect of sudden increase in ticket availability on the primary channel due to an unexpected buyback from the brokers, opening a window to investigate the causal effect of supply changes across the channels.

We are experiencing a time in which advances in information technology change everything around us. Almost every aspect of our work and life, from daily travel to grocery shopping, is now or will soon be connected to the internet. This drastic change has led to the emergence of many new products that display network effects, meaning that individual consumers value a product more when more other consumers use the same product. At the same time, development of data storage/processing tools offers a great chance for many firms to collect large amounts of data and understand their customers' purchasing behavior. For these firms, a significant challenge --- as well as opportunity --- is to develop models of customer choice behavior that incorporate network effects and to use such models to make better pricing decisions. This dissertation addresses the development and analysis of some such models. We consider a seller's problem of determining revenue-maximizing prices for an assortment of products that exhibit network effects. Customers make purchase decisions according to a multinomial logit (MNL) choice model, modified --- to incorporate network effects --- so that the utility each individual customer gains from purchasing a particular product depends on the market's total consumption of that product. In the setting of homogeneous products, we show that if the network effect is comparatively weak, then the optimal pricing decision of the seller is to set identical prices for all products. However, if the network effect is strong, then the optimal pricing decision is to set the price of one product low and to set the prices of all other products to a single high value. This pricing scheme boosts the sales of the single low-price product in comparison to the sales of all other products. The analysis is also extended to settings with heterogeneous products, and we show that optimal solutions have a structure similar to that found in the homogeneous case: either maintain a semblance of balance among all products, or boost the sales of just one product. Based on this structure, we propose an effective computational algorithm for such general heterogeneous settings. Subsequently, we study the preceding pricing problem from a robust optimization perspective. Unlike the classical MNL model where products' prices and sales have a one-to-one correspondence, in the MNL model with network effects a fixed set of prices may not uniquely determine sales. This occurs because, for given prices, sales arise as the solution to an equilibrium condition. In some cases, there may be multiple sales levels that satisfy the equilibrium condition. Among those sales equilibria corresponding to a given set of prices, we call the one with the highest revenue the ``optimistic" equilibrium, and the one with the lowest revenue the ``pessimistic" equilibrium. In our initial study mentioned in the previous paragraph, we implicitly took an ``optimistic" approach. We next take the pessimistic attitude and study the revenue-maximizing problem in the pessimistic setting. In the case that there is only one product to sell, the problem has the same pessimistic optimal price as the optimistic one, when the network effect is relatively weak. However, when the network effect is strong, the optimal policy requires the seller to become more conservative and the pessimistic optimal price is lower than the optimistic one. In the case that there are two products, the structure of equations at equilibrium becomes more complicated and we are not able to derive an analytical solution. To numerically solve this problem, two directions for finding the pessimistic optimal solution are proposed: divide and search, and linear relaxation. In addition, our numerical studies show that when the network effect is strong, the revenue from offering exactly one product is almost as good as that from selling an assortment of multiple products. This suggests that a company selling multiple products with strong network effects may be wise to simply offer just one product.

Latent variable models are an important aspect of consumer research whenever the determinants of behavior are an important aspect of study. The purpose of this thesis is to develop a new method of error augmentation to deal with latent variable models of heterogeneous, non-linear consumer behavior. This thesis comprises three essays. The first essay develops a new method of error augmentation for state-space models of economic behavior where the observed behavior is related to a latent variable whose temporal variation is described by a state equation. The proposed is applied to analyze a consumer’s purchase and resignation decisions in a membership club. The result indicates that increasing inter-arrival time between shipments can lead to longer customer longevity and greater sales. In the second essay, a state-space model is proposed to investigate the possibility to model inter-purchase times as an independent variable. The results indicate that the proposed state-space model can accurately describe customer behavior when the specification of the state equation is plausible for the data. In the third essay, a demand model is developed to treatment effects, line extension, and, the consumer decisions of brand-pack and no-choice for consumer packaged goods at the level of stock-keeping unit. The proposed model is illustrated with a panel data of a product category of consumer packaged goods. The results indicate that media can make some consumers have extreme preferences, and make preferences of some consumers become more homogeneous. This thesis contributes marketing literature by developing a new method of error augmentation for latent variable models that cannot be estimated by standard approaches. The new method of error augmentation is illustrated by three different marketing applications in this thesis.