Machines learn neuromarketing: Improving preference prediction from self-reports using multiple EEG measures and machine learning

A basic aim of marketing research is to predict consumers’ preferences and the success of marketing campaigns at the population-level. However, traditional marketing tools have various limitations, calling for novel measures to improve predictive power. In this study, we use multiple types of measures extracted from electroencephalography (EEG) recordings and machine learning (ML) algorithms to improve preference prediction based on self-reports alone. Subjects watched video commercials of six food products as we recorded their EEG activity, after which they responded to a questionnaire that served as a self-report benchmark measure. Thereafter, subjects made binary choices over the food products. We attempted to predict within-sample and population level preferences, based on subjects’ questionnaire responses and EEG measures extracted during the commercial viewings. We reached 68.5% accuracy in predicting between subjects’ most and least preferred products, improving accuracy by 4.07 percentage points compared to prediction based on self-reports alone. Additionally, EEG measures improved within-sample prediction of all six products by 20%, resulting in only a 1.91 root mean squared error (RMSE) compared to 2.39 RMSE with questionnaire-based prediction alone. Moreover, at the population level, assessed using YouTube metrics and an online questionnaire, EEG measures increased prediction by 12.7% and 12.6% respectively, compared to only a questionnaire-based prediction. We found that the most predictive EEG measures were frontal powers in the alpha band, hemispheric asymmetry in the beta band, and inter-subject correlation in delta and alpha bands. In summary, our novel approach, employing multiple types of EEG measures and ML models, offers marketing practitioners and researchers a valuable tool for predicting individual preferences and commercials’ success in the real world.     

Internal analysis of market structure: Recent developments and future prospects

The predominant paradigm in marketing for explaining buyer choice behavior is that choices reflect buyer evaluations of the attributes possessed by alternatives. Internal market structure analysis seeks to recover the attributes, and the buyer evaluations of those attributes, that govern brand choices. This essay briefly reviews some of the most recent developments in internal market structure analysis and discusses prospects for further work. This review was instigated by a four-day workshop on spatial representations of choice bahavior at the Banff Invitational Symposium on Consumer Decision Making and Choice Behavior, May 11–14, 1990. The workshop participants were: J. Douglas Carroll (Rutgers), Lee G. Cooper (UCLA), Terry Elrod (then of Vanderbilt Univ., now of the Univ. of Alberta), Eugene Kaciak (Brock Univ.), David B. MacKay (Indiana Univ.), and D. Sudharshan (Univ. of Illinois at Urbana-Champaign). This paper benefited from the insights of all of the participants, from helpful comments by Wayne S. DeSarbo, Greg M. Allenby, Donald R. Lehmann, and William L. Moore and from the assistance of Christopher Dubelar.     

Towards hierarchical linking of marketing resource allocation to market areas and product groups

In this paper a marketing resource allocation model is developed that is intended as a decision support tool for management at a country level in a multinational multiproduct firm. At the same time overall company objectives and portfolio considerations are taken into account by imposing a set of constraints on the countries. Output of the models from the different countries can help corporate management in allocating resources to countries and in evaluating the short term opportunity cost of its strategic constraints. As such, the model is seen as a first step in working towards hierarchically linked allocation models.     

Putting one-to-one marketing to work: Personalization, customization, and choice

The tailoring of a firm’s marketing mix to the individual customer is the essence of one-to-one marketing. In this paper, we distinguish between two forms of one-to-one marketing: personalization and customization. Personalization occurs when the firm decides what marketing mix is suitable for the individual. It is usually based on previously collected customer data. Customization occurs when the customer proactively specifies one or more elements of his or her marketing mix. We summarize key challenges and knowledge gaps in understanding both firm and customer choices in one-to-one markets. We conclude with a summary of research opportunities.     

Marketing,Existential Malpractice and an Etherised Discipline: A Soteriological Comment

This paper reviews the state of marketing theory and practice. A early reviewer of this paper was inclined to "criticise the title on the grounds of obscurity", but concluded it would do as it was. In an academic culture in which the average journal contents page is hardly less obfuscatory, our attempt at irony in the title and introduction seems to have been insufficiently extreme to make our point, which is that marketing academia talks esoterically to itself, even in journals such as this which aim to have a dual practitioner and academic audience. We discuss how this has left consultants as serial fad peddlers, perhaps with more influence but delivering dubious genuine benefit. The result is that marketing practice shows few signs of improving over time. We discuss the vital choices that need to be made in the nature and process of marketing if it is to reach out of its functional silo to seize the heart of the organisation.     

Feeding Fido: Changing Consumer Food Preferences Bring Pets to the Table

Consumers increasingly demand premium foods that satisfy particular lifestyle requirements. Simultaneously, premium pet foods lead the $18 billion U.S. pet food market. Using a Heckman two-stage decision model, we investigate the relationship between consumers’ food choices for themselves and food choices for their pets. Premium human food consumers with higher education and incomes are more likely to purchase premium pet food. This study also reveals a surprising age cohort effect: younger consumers are more likely to purchase premium pet food, despite budget constraints. The findings have implications for pet food marketing strategies. They also suggest an expected increase in demand for pet food ingredient transparency and pet food safety policy.     

Book Reviews

In a world of limited resources, marketing managers tasked to deliver shareholder value face decisions about how to maximise the returns on their marketing portfolio. Risk is less often considered. In finance the picture is very different; financial portfolio management is concerned with both risk and returns. The central innovation in this paper is the application of modern portfolio theory (MPT) to the management of marketing portfolios in food retailing and in drinks manufacturing. The authors develop a model that calculates an efficient frontier of marketing portfolios that maximise overall return within certain risk constraints, first for a simple two-segment marketing world and then for a more realistic multi-segment portfolio. However, marketing portfolios differ from financial ones in the sense that the allocation of marketing spend affects the returns from the portfolio. Therefore, a second innovation, an extension of MPT to take account of marketing spend allocation decisions, has been developed. Using this model, marketers can determine the risk and the returns of marketing investments, helping them select an optimal portfolio. This would go some way to ensuring that marketing contributes to shareholder value creation, currently one of its major challenges.     

The Establishment of Global Marketing Strategic Alliances by Small and Medium Enterprises

Within the constraints of financial resources, it remains possible for SMEs to find ways of cultivating their global marketing activities. Based on the balanced scorecard concept, we are able to develop a model, under a two-stage diagnostic process of subjective and objective conditions, to assist SMEs in making the best available choice in their global marketing activities.Following on from our examination of Taiwanese SMEs, this empirical study proposes four types of global marketing activities: the setting up of upstream and downstream joint after-sales service centers; the establishment of joint distribution warehouses; the development of products with regional characteristics; and the building of domestic and global retail distribution channels.     

Experiments on strategic choices and markets

Much of experimental research in marketing has focused on individual choices. Yet in many contexts, the outcomes of one’s choices depend on the choices of others. Furthermore, the results obtained in individual decision making context may not be applicable to these strategic choices. In this paper, we discuss three avenues for further advancing our understanding of strategic choices. First, there is a need to develop theories about how people learn to play strategic games. Second, there is an opportunity to enrich standard economic models of strategic behavior by allowing for different types of bounded rationality and by relaxing assumptions about utility formulation. These new models can help us to more accurately predict strategic choices. Finally, future research can improve marketing practice by designing better mechanisms and validating them using experiments.     

What really matters in attraction effect research: when choices have economic consequences

Researchers have recently strongly questioned the robustness of the attraction effect, according to which adding a decoy option to an existing choice set affects consumers’ choice behavior. Tying in with this debate, we identify the persistent use of hypothetical choices in the domain to be a major shortcoming in attraction effect research. In an experiment on the attraction effect with a realistic choice setting that fosters external validity, we manipulate the choice framing by contrasting hypothetical choices with binding choices that entail economic consequences. We find the attraction effect to be much stronger when decisions are binding, underlining the effect’s usefulness as a marketing tool.     

The impact of internal,external, and competitor factors on marketing strategy performance

ABSTRACT

Strategy formulation is commonly understood as the match between a firm’s internal resources and skills and its external environment. Marketing strategy performance is the function of a dynamic, interactive process incorporating internal firm resources, external environmental factors, and competitive actions. The study aims to assess the impact of competitor actions on marketing strategy performance. We develop a model that accommodates the effects of 29 variables (comprising internal marketing strategy variables, external environmental factors and competitors’ marketing mix variables) on business performance. We empirically test the model using simultaneous equation modelling of time-series data on UK car manufacturers collected from publically available resources and annual reports. The results show that external factors, in particular competitors’ marketing mix elements, have a greater influence on a company’s business performance than internal (marketing and non-marketing) strategy variables. Implications for marketing theory and management are discussed.     

Practice Makes Profit: Business Practices and Firm Success

Which business practices set successful firms apart from others? We address this question using data from an official survey of almost 3000 New Zealand firms. Questions cover: leadership, planning practices, customer and supplier focus, employee practices, quality and process monitoring, benchmarking, community and social responsibility, innovation, IT use, business structure and the competitive environment. Some of these are internal practices reflecting a firm’s resources and capabilities; some are characteristics of the external environment. We find that capital investment choices, R&;D practices, market research and a range of employee practices are positively associated with firm success; industry structure is also a key determinant of success. The association between specific business practices and firm success is mostly independent of firm size, age and industrial sector, other than for export marketing.     

大型零售商整合渠道资源:动因与路径

当前,大量营销实践表明,稳固的营销渠道是大型零售商提高经营效率,获取市场竞争力的重要前提。本文主要运用交易成本、委托代理、企业战略、服务营销等理论进行分析,指出大型零售商企业整合渠道资源的动因是拓宽和构建稳固的营销渠道。同时,结合案例分析认为,大型零售商整合渠道资源的主要路径包括:与供应商建立战略联盟、委托制造商生产自有品牌产品、并购同行竞争者、通过特许加盟进行连锁经营、采取业态多元化策略、对消费者开展服务营销等。最后,就每种整合路径中存在的难点与关键进行了分析。     

Performance implications of market orientation,marketing resources,and marketing capabilities

Abstract

Drawing on the competitive capability theory, this paper examines how market orientation, marketing resources, and marketing capabilities contribute to firm performance. The empirical results show that being market oriented influences the level of marketing resources firms possess and the capability to deploy such resources. The findings show marketing resources and marketing capabilities are significant drivers of firm performance, and their impact is greater when they are complementary to each other.     

Applications of evolutionary psychology in marketing

Evolutionary psychology is an emerging paradigm in psychological science. The current article introduces this framework to marketing scholars and presents evidence for its increasing acceptance within the social science community. As a result, a case is made for the application of evolutionary psychology to marketing, and especially consumer behavior. Application of the evolutionary framework in studying gender‐related consumption behavior is illustrated by comparing the evolutionary predictions with results obtained from previous studies, by supporting these predictions with market‐level consumption data, and by proposing new hypotheses based on this framework. Also discussed are the potential applications of evolutionary psychology to other consumption‐related phenomena like evaluation of endorser attractiveness in advertising, biologically driven consumption choices among women, consumer‐experienced emotions in service encounters, and consumption choices as inclusive fitness maximization rather than utility maximization. © 2000 John Wiley & Sons, Inc.     

Environmental consumerism: A process of children's socialization and families' resocialization

The development and impact of children's concern for the environment is addressed. A model is presented that illustrates that such development may be based upon children's cognitive status, their exposure to nature, and their exposure to particular socializing influences. One of the possible outcomes of children's concern for the environment is that they may become catalysts for family environmental consumerism, and thereby influence related family attitudes and decision-making. We propose that environmental consumerism may be moderated by the nature of family communication patterns, which can affect the possibility of family resocialization regarding environmental concerns. In addition, family resources are also expected to moderate the degree of family environmental consumerism. We suggest that environmental consumerism will be reflected in both purchasing and recycling choices and behavior. Consequently, marketing implications are also addressed. © 1995 John Wiley & Sons, Inc.     

Sequential sampling models of choice: Some recent advances

Choice models in marketing and economics are generally derived without specifying the underlying cognitive process of decision making. This approach has been successfully used to predict choice behavior. However, it has not much to say about such aspects of decision making as deliberation, attention, conflict, and cognitive limitations and how these influence choices. In contrast, sequential sampling models developed in cognitive psychology explain observed choices based on assumptions about cognitive processes that return the observed choice as the terminal state. We illustrate three advantages of this perspective. First, making explicit assumptions about underlying cognitive processes results in measures of deliberation, attention, conflict, and cognitive limitation. Second, the mathematical representations of underlying cognitive processes imply well documented departures from Luce’s Choice Axiom such as the similarity, compromise, and attraction effects. Third, the process perspective predicts response time and thus allows for inference based on observed choices and response times. Finally, we briefly discuss the relationship between these cognitive models and rules for statistically optimal decisions in sequential designs.     

Discrete choice models of firms’ strategic decisions

This paper outlines the methods and applications related to the nascent area of empirical discrete games in marketing. Many key strategic decisions firms make involve discrete choices such as deciding the location of a new store, determining where in product space to position a product, or what options to offer in a service contract. These decisions are fairly complex and typically involve the consideration of a number of demand, cost, and competitive factors. What makes these discrete choices particularly interesting (and challenging to analyze) is that they are interrelated with the choices of other firms because firms take into account the actions of their competitors when making their own decisions. We describe the basic problem of dealing with interrelated discrete choices in a game-theoretic framework and present the various estimation methods available. A discussion of the existing applications and future research opportunities concludes the article.     

Who Shops Where?

Abstract

The Food Industry Research and Development Institute conducted a nationwide survey of 1,200 consumers in Taiwan in 1999. We apply stepwise logistic regression to identify significant sociodemographic factors, such as gender, age, and others, which sway the choice of each of six major types of food markets and to identify promotional factors which positively or negatively influence consumers' preferences for that outlet. For the six market types, sociodemographic factors affect consumers' choices of markets differently in each case, but marketing factors also influence choices of which type of marketplace to use most frequently.