Empirical Marketing Research Research Articles

Machine learning and AI in marketing – Connecting computing power to human insights

Artificial intelligence (AI) agents driven by machine learning algorithms are rapidly transforming the business world, generating heightened interest from researchers. In this paper, we review and call for marketing research to leverage machine learning methods. We provide an overview of common machine learning tasks and methods, and compare them with statistical and econometric methods that marketing researchers traditionally use. We argue that machine learning methods can process large-scale and unstructured data, and have flexible model structures that yield strong predictive performance. Meanwhile, such methods may lack model transparency and interpretability. We discuss salient AI-driven industry trends and practices, and review the still nascent academic marketing literature which uses machine learning methods. More importantly, we present a unified conceptual framework and a multi-faceted research agenda. From five key aspects of empirical marketing research: method, data, usage, issue, and theory, we propose a number of research priorities, including extending machine learning methods and using them as core components in marketing research, using the methods to extract insights from large-scale unstructured, tracking, and network data, using them in transparent fashions for descriptive, causal, and prescriptive analyses, using them to map out customer purchase journeys and develop decision-support capabilities, and connecting the methods to human insights and marketing theories. Opportunities abound for machine learning methods in marketing, and we hope our multi-faceted research agenda will inspire more work in this exciting area.

Consumer dynamics: theories, methods, and emerging directions

Consumer attitudes and behaviors are fundamentally dynamic processes; thus, understanding consumer dynamics is crucial for truly understanding consumer behaviors and for firms to formulate appropriate actions. Recent history in empirical marketing research has enjoyed increasingly richer consumer data as the result of technology and firms’ conscious data collection efforts. Richer data, in turn, have propelled the development and application of quantitative methods in modeling consumer dynamics, and have contributed to the understanding of complex dynamic behaviors across many domains. In this paper, we discuss the sources of consumer dynamics and how our understanding in this area has improved over the past four decades. Accordingly, we discuss several commonly used empirical methods for conducting dynamics research. Finally, as the data evolution continues into new forms and new environments, we identify cutting-edge trends and domains, and offer directions for advancing the understanding of consumer dynamics in these emerging areas.

Universal dimensions of individuals' perception: Revisiting the operationalization of warmth and competence with a mixed-method approach

A dynamic and growing body of marketing literature draws from the Stereotype Content Model's (SCM) dimensions, warmth and competence, to describe individuals' perception of various market-related stimuli (e.g., salespeople, employees, products) and predict their influence on subsequent behavior. However, the operationalization of these fundamental dimensions in empirical marketing research has been inconsistent and problematic, hindering comparability of findings across studies and limiting the overall usefulness of warmth–competence in relevant research. Using a mixed-method approach, the present paper scrutinizes the warmth–competence dimensions in order to validate and optimize their measurement. Through seven studies using different methodologies and metrics, we identify a set of trait items that (a) capture perceptions of warmth and competence consistently across a variety of impression formation settings, and (b) display strong psychometric properties. Our findings offer a parsimonious approach that promotes the consistent operationalization of warmth and competence across marketing studies and enables the integration of empirical findings, both of which are crucial requirements for meta-analytic investigations, replication studies, and integrative reviews.

Underpricing in Privatized Public Offerings: The Indian Experience

Underpricing of IPOs is the sale of shares at low prices and it is a well-documented fact of empirical equity market research. Present study aims to examine the same by estimating the magnitude of underpricing in disinvestment oriented IPOs and FPOs. Along with this, it also aims to compare the degree of underpricing across IPOs and subsequent stages of FPOs. Total number of IPO and FPO cases to be analyzed are 46 (8 IPO, 25 FPO-I, 10 FPO-II, 3 FPO-III) which have been introduced during 2003-2017 by Govt-owned enterprises in India. Market adjusted excess return methodology has been used to compute underpricing. Results depict that underpricing do exists in privatized public offerings. The study also witness the reduced underpricing levels from IPO to third stage of FPO which indicate towards high cost of raising equity at IPO and gets reduced at subsequent stages of FPOs. Based on the findings, the research recommends that divestment activity should spread over different stages of offerings i.e. IPOs and FPOs. This research contributes to the literature by estimating and comparing the magnitude of underpricing in “privatized” public offerings and provides the Governmental institutions and investors with the base and information to make appropriate decisions.

Personality or Value: A Comparative Study of Psychographic Segmentation Based on an Online Review Enhanced Recommender System

Big consumer data promises to be a game changer in applied and empirical marketing research. However, investigations of how big data helps inform consumers’ psychological aspects have, thus far, only received scant attention. Psychographics has been shown to be a valuable market segmentation path in understanding consumer preferences. Although in the context of e-commerce, as a component of psychographic segmentation, personality has been proven to be effective for prediction of e-commerce user preferences, it still remains unclear whether psychographic segmentation is practically influential in understanding user preferences across different product categories. To the best of our knowledge, we provide the first quantitative demonstration of the promising effect and relative importance of psychographic segmentation in predicting users’ online purchasing preferences across different product categories in e-commerce by using a data-driven approach. We first construct two online psychographic lexicons that include the Big Five Factor (BFF) personality traits and Schwartz Value Survey (SVS) using natural language processing (NLP) methods that are based on behavior measurements of users’ word use. We then incorporate the lexicons in a deep neural network (DNN)-based recommender system to predict users’ online purchasing preferences considering the new progress in segmentation-based user preference prediction methods. Overall, segmenting consumers into heterogeneous groups surprisingly does not demonstrate a significant improvement in understanding consumer preferences. Psychographic variables (both BFF and SVS) significantly improve the explanatory power of e-consumer preferences, whereas the improvement in prediction power is not significant. The SVS tends to outperform BFF segmentation, except for some product categories. Additionally, the DNN significantly outperforms previous methods. An e-commerce-oriented SVS measurement and segmentation approach that integrates both BFF and the SVS is recommended. The strong empirical evidence provides both practical guidance for e-commerce product development, marketing and recommendations, and a methodological reference for big data-driven marketing research.

Endogeneity and marketing strategy research: an overview

Endogeneity in empirical marketing research is an increasingly discussed topic in academic research. Mentions of endogeneity and related procedures to correct for it have risen 5x across the field’s top journals in the past 20 years, but represent an overall small portion of extant research. Yet there is often substantial difficulty in reconciling issues of endogeneity with many of the substantive questions of interest to marketing strategy for both theoretical and/or practical reasons. This paper provides an overview of main causes of endogeneity, approaches to addressing it, and guidance to marketing strategy researchers to balance these issues as the field continues to move towards more methodological sophistication, potentially at the expense of managerial tractability.

Missing Data - Better "Not to Have Them", but What If You Do? (Part 1)

Missing values are ubiquitous in empirical marketing research. If missing data are not dealt with properly, this can lead to a loss of statistical power and distorted parameter estimates. While traditional approaches for handling missing data (e.g., listwise deletion) are still widely used, researchers can nowadays choose among various advanced techniques such as multiple imputation analysis or full-information maximum likelihood estimation. Due to the available software, using these modern missing data methods does not pose a major obstacle. Still, their application requires a sound understanding of the prerequisites and limitations of these methods as well as a deeper understanding of the processes that have led to missing values in an empirical study. This article is Part 1 and first introduces Rubin’s classical definition of missing data mechanisms and an alternative, variable-based taxonomy, which provides a graphical representation. Secondly, a selection of visualization tools available in different R packages for the description and exploration of missing data structures is presented.

Market-Oriented Service Network Design When Demand is Sensitive to Congestion

In this paper, we present a market-oriented service network design model in which the seller’s problem is to determine how many facilities to open, where to locate them, and which service capacities and service levels they should have to maximize overall profit. Our model explicitly considers the customers’ facility choice as a function of typical choice determinants, such as travel distance and congestion delays (which are endogenously impacted by the seller’s decisions) as well as other, exogenous factors such as price level and product variety. We relax the assumption adopted in many related works that the service provider has discretion as to the assignment of customers to facilities; instead, we allow customers to self-select based on their preferences for facility attributes according to an attraction-based choice model. Furthermore, we capture not only the effect of congestion on demand but also the reciprocal impacts of demand on congestion and service level by modeling each facility as an M/G/1 queue with service capacity as a decision variable. The resulting model represents a non-linear mixed-integer problem (MIP); however, we show that this problem can be linearized introducing several new continuous variables and constraints. To solve the linearized MIP to proven optimality or approximately, we develop an exact decomposition approach and heuristics. We report the performance testing of our approach with regard to run times and solution quality in an extensive computational experiment. A case study of the selection of locations for new convenience stores in Heidelberg, Germany illustrates the real-world applicability of the model using empirical market research data. An equivalent problem arises in a number of other applications, particularly in service shop industries such as restaurants and retailers. Surprisingly, profit maximization under customer-choice-driven behavior has rarely been considered as an objective in the related literature. The online appendix is available at https://doi.org/10.1287/trsc.2017.0797 .

Discriminant validity assessment in marketing research

Establishing discriminant validity has been a keystone of measurement validity in empirical marketing research for many decades. Without statistically showing that constructs have discriminant validity, contributions to marketing literature are likely to foster the proliferation of constructs that are operationally the same as other constructs already present in the literature, thus leading to confusion in the development of theory. This article addresses this concern by evaluating well-established methods for testing discriminant validity through the simulation of artificial datasets (containing varying levels of correlation between constructs, sample size, measurement error, and distribution skewness). The artificial data are applied to six commonly used approaches for testing the existence of discriminant validity. Results strongly suggest that several methods are much more likely than others to yield accurate assessments of whether discriminant validity exists, especially under specific conditions. Recommendations for practice in the assessment of discriminant validity are suggested.

Control Variables in Marketing Research

In empirical marketing research that does not rely on fully randomized experiments, control variables are an important tool to rule out rival alternative explanations for the observed relationships. Despite their importance for causal inference, control variables often receive little attention from either applied researchers or methodologists. At the same time, over-views of control variable practices in neigh-boring disciplines demonstrate that researchers struggle with selecting, analyzing, and interpreting control variable results. In response, this article combines a synthesis of the theoretical knowledge on control variables with a review of control variable practices. Against this background, we develop and discuss sixteen recommendations for control variable use in marketing research.

QCA in empirical marketing research: An experiment featuring Dorah Explorah, investigating celebrity endorsement's effect on product selection

This study explains how to disentangle the relationships between outcomes and the configurations of marketing brand tactics and consumer attributes for a particular marketing phenomenon. We demonstrate that qualitative comparative analysis (QCA) can be implemented in marketing contexts, and that it can explain marketing phenomena to the standards of rigour, generality and complexity demanded by scientific research. Fuzzy set QCA (fsQCA) need not be feared; it can be a very useful case-based method for marketing theorists. The “thought experiment” featuring the hypothetical Dorah Explorah brand demonstrates fsQCA's value and its similitude with real markets, and confirms that a single attribute, marketing tactic or condition can affect the examined outcome differently when it is part of a different configuration, although it may not be necessary or sufficient for the outcome by itself. We extend the literature on marketing theory creation by drawing on social psychology and management disciplines (for methodology) and Heider's (1958) balance theory to propose a specific hypothesis. We then test this hypothesis via an experimental manipulation. We present the theoretical background supporting the study's hypothesis and make a strong plea for marketing scholars to develop theories using truly useful, highly predictive asymmetrical logic. We hope that this paper will act as a tutorial for marketing researchers, novices and experts, making the application of fsQCA as a methodology and as a set of techniques easier and more transparent. We explicitly highlight the configurationally important aspects of qualitative research in empirical marketing studies and comparative scientific enquiry.

MARKETINGOVÝ VÝZKUM A IMAGE MÍSTA

The paper deals with some problems of the image and identity of two towns (Brno and Zlín) as well as the whole country (Czech Republic). It starts with theoretical explanation of terms place image, identity and culture and its interrelated influences. Than own empirical marketing research of Brno image is presented and compared with theory of marketing communication, especially with the problems of place identity, unified visual style and logo.

Nash Equilibria of Co-Operative Advertising Programs with Advertising Threshold Effects

As an important advertising phenomenon which has been proven by previous empirical marketing research, the advertising threshold effect implies that advertising has little effect on sales when advertising investment is beneath a certain level. In this paper, we focus on a cooperative advertising program, in which a manufacturer shares part of its retailer’s advertising cost, to illustrate the impact of the advertising threshold effect. Dividing the advertisement efforts into national and local advertising, we propose a new advertising response model which can describe the advertising threshold effect well. Based on the advertising response function, we derive the manufacturer’s and the retailer’s equilibrium advertising investments when they play a Nash game. From the analysis we find that there are four possible Nash equilibria when we take the advertising threshold effect into account. We derive the sufficient and necessary conditions under which each of the four possible equilibria is a Nash equilibrium, and explain these conditions with examples from practice. Another interesting result is that there are two different equilibria when certain conditions are satisfied.

Is there a tacit acceptance of student samples in marketing and management research?

The evaluation criteria for most marketing and management journals underline the importance of student samples' characteristics and how well they represent the population being studied. However, the predominance of student samples in empirical marketing and management research is sufficient proof of the divergence between theoretical requirements and practical implementation. Despite the theoretical and empirical objections, several authors claim that there is a noticeable tacit acceptance of student samples, even in top research societies. However, generalisations are only feasible if the replication of research is carried out with non-student subjects. This paper analyses the status quo of the usage of student samples in the most reputable marketing and management research journals. In doing so, we want to resume the discussion on student sampling, which has been dormant during the last few years. Our results provide some evidence that top-tier journals still rely strongly on student samples.

The role of vocational education and training curricula in economic development

Globalization has become one of the crucial topics of discussion and concern in recent times, since it has a decisive impact upon our lives. Therefore, if we are to compete on the global stage and meet the globalization challenges successfully we need to make significant improvements in terms of maximizing the effectiveness of the vocational education and training instruction based on specific design of curricula. It is widely accepted that we live in a world where knowledge and technologies are renewed at an accelerating pace. To respond to the resulting updated requirements of economic trends and goals, our educational planning has to be shifted to new forms of instructional content and delivery. Consequently, globalization and the new emerging economic and social order demand new policies and strategies to educational processes. To this effect, the educational and training reforms have to be based on the market needs assessment identified by appropriate market research. This paper refers to the findings of such a research conducted in order to specify the needs that will have to be satisfied through the implementation of Technical and Vocational Education and Training (TVET) programmes which are considered to be the most effective instruments of meeting globalization demands. The problem statements consisted of three major types of questions: (a) Will school alone achieve the goals of competencies-based education? (causal) (b) To what extent should formal education prepare people to work? (relationship) and (c) To what extent should vocational education and training respond to work? (impact).The purpose of this study-research is to analyse the findings of the empirical market research and proceed to the recommendation of specific curricula design to enhance the effectiveness of TVET. A sample of 1250 persons being senior administrative officers and clerical staff were surveyed. A questionnaire was distributed to all the employees and an interview was followed. In this way, based on the findings and results, it has been possible to integrate professional knowledge with empirical data in order to form instructional developmental decisions. Finally, in the conclusions and recommendations sectors the data identified by the research are described in detail and analyzed so that to ensure that the chain relationship of market research > curriculum design > vocational education and training will be effective and successful.

Assessing brand image through communalities and asymmetries in brand-to-attribute and attribute-to-brand associations

Abstract Brand image is a key component of customer-based brand equity, and refers to the associations a consumer holds in memory. Such associations are often directional; one should distinguish between brand-to-attribute and attribute-to-brand associations. Information on these associations arise from two ways of collecting data, respectively: brand-by-brand evaluations of all attributes and attribute-by-attributes evaluations of all brands. In this paper, the authors present a methodological approach, namely correspondence analysis of matched matrices, to assess the communalities as well as asymmetries between brand-to-attribute and attribute-to-brand associations. This allows studying whether or not there is match in a brand’s positioning (brand-to-attribute associations) and relative advantage (attribute-to-brand associations). The methodology results in perceptual maps visualizing brand image. The approach is illustrated in an empirical market research project in which two samples of consumers evaluated ten brands of deodorants and eleven attributes. The stability of the solution is examined using bootstrap resampling procedures.

Diffusion of Measurement Invariance Assessment in Cross-National Empirical Marketing Research: Perspectives from the Literature and a Survey of Researchers

The authors examine (1) the extent to which cross-national marketing scholars report measurement invariance (MI) assessment results and (2) what cross-national marketing scholars think about MI assessment in general. In Study 1, the authors analyze all cross-national empirical articles (243) published in 15 well-respected and peer-reviewed marketing journals from 2000 to 2005. Although the results indicate a steady growth of published cross-national empirical marketing research and assessment of MI, only 28% of the studies undertook the procedure. In Study 2, the authors analyze responses from 86 cross-national empirical marketing scholars regarding their knowledge about, attitudes toward, and use of MI assessment. The results indicate that the relatively low utilization of MI assessment is due to low MI knowledge and the sophistication of the techniques. The authors conclude with suggested implications for the field of international marketing and a discussion of future research directions.

Messung in der Marketingforschung — Status Quo und Perspektiven

Latent constructs are important elements of modern theories in empirical marketing research. The underlying latent variables are, generally, modelled as quantitative variables. The measurement of latent variables entails two distinct problems. Firstly, evidence has to be provided that the latent variable really exists as a quantity and that it is, consequently, measurable. Secondly, a concrete measurement instrument has to be devised that enables us to infer measures of latent variables from observations of manifest variables. The predominant measurement paradigm of classical test theory fails to provide this sort of evidence. It rather presumes measurement. Recently, the discussion of models with formative indicators has gained momentum again. Typically, formative indicators are seen as an alternative to reflective indicators entailed by classical test theory. The analysis of criteria for choosing the appropriate model (reflective or formative) that are offered in the literature shows that these criteria do not allow for a decision based on empirical evidence. Finally, formative indicators turn out to be incompatible with the notion of a real, truly existing latent variable. Thus, formative models are no alternative to reflective measurement models. By their nature, they are models of structural relationships, i.e. they pertain to structural theories. A scientifically satisfactory solution to the problem of measuring latent variables has to be based on a definition of measurement that is compatible with the scientific concept of quantity. With the Rasch model, item response theory offers a class of models which comply with the requirements of the classical concept of quantity.

A gallery of misapprehensions: the importance of survey research in political and social decisions

The 20th century is often hailed as the great century of social research. A list of all of the pioneering milestones in the field of social research could just go on and on: the inspiration empirical social researchers have gained from the methods and findings in the field of psychology; the methodological advances that accompanied the blossoming of empirical market and media research; the development of other new tools in the field of empirical social research, especially the combination of media content analysis and the survey method; the tremendous advances in computer-aided data analysis—all of these are indisputable accomplishments of the 20th century. Despite all of these advances, however, empirical social research has yet to establish itself in society or even across broad swaths of the scientific community. The greatest obstacle facing empirical social research today is that empirical thinking is still not commonplace among most social scientists and politicians. This paper was presented at the WAPOR Seminar “Current Perspectives in Polling” at the Escola Superior de Comunicação Social, Lisbon, March 21, 2005.

Relational Exchange Norms in Marketing: A Critical Review of Macneil’s Contribution

Different theories make different assumptions about the mechanisms that govern economic transactions and there are several reviews that have summarized existing conceptual and empirical work associated with such frameworks as transaction cost analysis or agency theory. However, Macneil’s Relational Contracting Theory, another major theoretical foundation of current marketing research into business relationships, has not yet received similar attention. This article provides a review of a core concept developed in this stream of literature: the norm concept. It contrasts Macneil’s view of norms with the work developed in the field of marketing. As a result, the authors identify, first, a gap between Macneil’s interpretation of the norm concept and the application made by marketing scholars and second, contradictions in the results obtained from empirical marketing research.