Sha Yang

An Empirical Analysis of Search Engine Advertising: Sponsored Search in Electronic Markets

The phenomenon of sponsored search advertising---where advertisers pay a fee to Internet search engines to be displayed alongside organic (nonsponsored) Web search results---is gaining ground as the largest source of revenues for search engines. Using a unique six-month panel data set of several hundred keywords collected from a large nationwide retailer that advertises on Google, we empirically model the relationship between different sponsored search metrics such as click-through rates, conversion rates, cost per click, and ranking of advertisements. Our paper proposes a novel framework to better understand the factors that drive differences in these metrics. We use a hierarchical Bayesian modeling framework and estimate the model using Markov Chain Monte Carlo methods. Using a simultaneous equations model, we quantify the relationship between various keyword characteristics, position of the advertisement, and the landing page quality score on consumer search and purchase behavior as well as on advertisers cost per click and the search engines ranking decision. Specifically, we find that the monetary value of a click is not uniform across all positions because conversion rates are highest at the top and decrease with rank as one goes down the search engine results page. Though search engines take into account the current periods bid as well as prior click-through rates before deciding the final rank of an advertisement in the current period, the current bid has a larger effect than prior click-through rates. We also find that an increase in landing page quality scores is associated with an increase in conversion rates and a decrease in advertisers cost per click. Furthermore, our analysis shows that keywords that have more prominent positions on the search engine results page, and thus experience higher click-through or conversion rates, are not necessarily the most profitable ones---profits are often higher at the middle positions than at the top or the bottom ones. Besides providing managerial insights into search engine advertising, these results shed light on some key assumptions made in the theoretical modeling literature in sponsored search.

Modeling Interdependent Consumer Preferences

A consumers preference for an offering can be influenced by the preferences of others in many ways, ranging from social identification and inclusion to the benefits of network externalities. In this article, the authors introduce a Bayesian spatial autoregressive discrete-choice model to study the preference interdependence among individual consumers. The autoregressive specification can reflect patterns of heterogeneity in which influence propagates within and across networks. These patterns cannot be modeled with standard random-effect specifications and can be difficult to capture with covariates in a linear model. The authors illustrate their model of interdependent preferences with data on automobile purchases and show that preferences for Japanese-made cars are related to geographically and demographically defined networks.

Bayesian Analysis of Simultaneous Demand and Supply

In models of demand and supply, consumer price sensitivity affects both the sales of a good through price, and the price that is set by producers and retailers. The relationship between the dependent variables (e.g., demand and price) and the common parameters (e.g., price sensitivity) is typically non-linear, especially when heterogeneity is present. In this paper, we develop a Bayesian method to address the computational challenge of estimating simultaneous demand and supply models that can be applied to both the analysis of household panel data and aggregated demand data. The method is developed within the context of a heterogeneous discrete choice model coupled with pricing equations derived from either specific competitive structures, or linear equations of the kind used in instrumental variable estimation, and applied to a scanner panel dataset of light beer purchases. Our analysis indicates that incorporating heterogeneity into the demand model all but eliminates the bias in the price parameter due to the endogeneity of price. The analysis also supports the use of a full information analysis.

The Effectiveness of Demographic and Psychographic Variables for Explaining Brand and Product Category Use

The predictive relationship of a large and comprehensive set of personal descriptors to aspects of product and brand use is examined. The descriptors comprise demographic and general psychographic variables frequently used in segmentation studies and studies of consumer purchase behavior. The evidence is overwhelming that the covariates are related to brand use in an identical way for all brands, indicating that they are not useful for predicting relative brand preference. The covariates are shown to be predictive of product use. Discussion of the explanatory content of the variables is offered.

Estimating Disaggregate Models Using Aggregate Data Through Augmentation of Individual Choice

In this article, the authors propose a Bayesian method for estimating disaggregate choice models using aggregate data. Compared with existing methods, the advantage of the proposed method is that it allows for the analysis of microlevel consumer dynamic behavior, such as the impact of purchase history on current brand choice, when only aggregate-level data are available. The essence of this approach is to simulate latent choice data that are consistent with the observed aggregate data. When the augmented choice data are made available in each iteration of the Markov chain Monte Carlo algorithm, the dynamics of consumer buying behavior can be explicitly modeled. The authors first demonstrate the validity of the method with a series of simulations and then apply the method to an actual store-level data set of consumer purchases of refrigerated orange juice. The authors find a significant amount of dynamics in consumer buying behavior. The proposed method is useful for managers to understand better the consumer purchase dynamics and brand price competition when they have access to aggregate data only.

Inertial Disruption: The Impact of a New Competitive Entrant on Online Consumer Search.

The objective of this article is to examine the impact of a new competitive entry on online consumer search behavior. The authors use store visitation as a measure of online search and decompose a shoppers tendency to search a given Web site into a baseline search preference for that site and an inertial effect of visiting that site. They find that inertia is an important driver in search behavior and is easily disrupted by a new competitive entry. This is a new and significant finding that contributes to the competitive entry literature. The authors develop a Bayesian model of search that separates the role of baseline search preference and inertia on store visitation and captures the effect of a new competitive entry. They apply this model to Internet clickstream data for the online bookstore market, in which they focus on the entry of Borders.com in 1998.

A Model for Observation, Structural, and Household Heterogeneity in Panel Data

Standard methods of understanding customer behavior in marketing allow for differences in sensitivity across consumers, but often assume that the sensitivity of a particular individual is fixed through time. In many situations, this assumption may not be valid. Both the importance of variables, and the manner that they are combined to form an overall measure of value for an offer, can change. In this paper we propose an approach of modeling a customers purchase history that allows identification of when these aspects of customer behavior are likely to change. This information is useful, for example, in planning when particular customers will be most likely to respond to an offer. Our approach nests common methods of dealing with individual differences, and allows for the introduction of covariates associated with changes in customer behavior. We illustrate our model with data from a national sample of credit card usage and adoption.

Analyzing search engine advertising: firm behavior and cross-selling in electronic markets

The phenomenon of sponsored search advertising is gaining ground as the largest source of revenues for search engines. Firms across different industries have are beginning to adopt this as the primary form of online advertising. This process works on an auction mechanism in which advertisers bid for different keywords, and final rank for a given keyword is allocated by the search engine. But how different are firms actual bids from their optimal bids? Moreover, what are other ways in which firms can potentially benefit from sponsored search advertising? Based on the model and estimates from prior work [10], we conduct a number of policy simulations in order to investigate to what extent an advertiser can benefit from bidding optimally for its keywords. Further, we build a Hierarchical Bayesian modeling framework to explore the potential for cross-selling or spillovers effects from a given keyword advertisement across multiple product categories, and estimate the model using Markov Chain Monte Carlo (MCMC) methods. Our analysis suggests that advertisers are not bidding optimally with respect to maximizing profits. We conduct a detailed analysis with product level variables to explore the extent of cross-selling opportunities across different categories from a given keyword advertisement. We find that there exists significant potential for cross-selling through search keyword advertisements in that consumers often end up buying products from other categories in addition to the product they were searching for. Latency (the time it takes for consumer to place a purchase order after clicking on the advertisement) and the presence of a brand name in the keyword are associated with consumer spending on product categories that are different from the one they were originally searching for on the Internet.

Market Segmentation Research: Beyond Within and Across Group Differences

Market segmentation research is currently focused too narrowly on the task of segment identification as opposed to its strategic relevance within a firm. In this paper we distinguish an ex ante approach to market segmentation research, which begins with studying the motivating conditions that lead people to the tasks and interests in their lives, from an ex post approach which begins with an individuals reaction to marketplace offerings. We argue that the marketing task of guiding managements to ‘make what people will want to buy’ will be more successful in light of a deep understanding of behavior in the context of everyday life and work, rather than a detailed understanding of preferences in the marketplace. Directions for future research are discussed.

Forecasting consumer credit card adoption: what can we learn about the utility function?

Abstract How to accurately predict customers’ adoption behavior is becoming more important and challenging to many credit card marketers as competition increases. This calls for more knowledge about the consumer utility function and the corresponding decision behavior. In this study, we challenge the commonly used logit model which implies linear utility function and constant marginal rate of substitution (MRS) with a neural network model that can accommodate nonlinear utility function and changing MRS between card attributes. Using the data from a national survey of credit card usage, we find that the neural network model significantly outperforms the logit in predicting consumer card adoption decisions. Our results indicate that consumers do not make linear tradeoffs between card attributes and the MRS between card features does not remain constant even within the same demographic group.