Applications of artificial neural networks in management science: a survey

An increasing number of publications reporting on applications of Artificial Neural Networks demonstrates the growing relevance of modeling techniques summarized under this heading. In Management Science several known problems also have already been solved by using one of these methods.The paper at hand provides a survey of the most recent publications in this field and employs the functional structuring of Management for presentation. In the spirit of a metaanalysis we try to identify regularities with respect to the methods used and the results achieved. Furthermore we formulate areas for future research and give a summarizing evaluation of the state-of-the-art.     

NFT marketing: How marketers can use nonfungible tokens in their campaigns

Nonfungible tokens (NFTs) are a record of ownership of primarily digital media, where the NFT is stored on a blockchain. According to the 2021 Gartner Hype Cycle for Key Technologies, NFTs may significantly transform marketing functions. Marketing managers wishing to adopt NFTs therefore need to know something about the marketing implications. This article explains NFTs in broad terms and discusses the marketing implications using a modified AIDA hierarchy. These implications can give marketing managers and executives guidelines on how to persuade consumers to purchase NFTs owing to their unique characteristics, such as scarcity, nonfungibility, proven authenticity, proof of ownership, royalties, and direct distribution infrastructure.     

Using social marketing to enhance hotel reuse programs

Hotels are increasingly sponsoring social marketing programs to encourage voluntary reduction of towel and linen use. These programs reduce water usage thus benefiting the environment. They also reduce hotels' laundering costs. Two controlled experiments were conducted to assess behavioral intentions and attributions as a result of such programs. Results demonstrate that response is most positive when savings from the program are donated to charity. When evidence is provided suggesting that a majority of hotel guests participate (social proof), the impact of how savings are used is reduced. This is especially pronounced for those traveling on business. Fit between the charity and the reuse program is inconsequential. The authors discuss implications.     

Robust risk aggregation with neural networks

We consider settings in which the distribution of a multivariate random variable is partly ambiguous. We assume the ambiguity lies on the level of the dependence structure, and that the marginal distributions are known. Furthermore, a current best guess for the distribution, called reference measure, is available. We work with the set of distributions that are both close to the given reference measure in a transportation distance (e.g., the Wasserstein distance), and additionally have the correct marginal structure. The goal is to find upper and lower bounds for integrals of interest with respect to distributions in this set. The described problem appears naturally in the context of risk aggregation. When aggregating different risks, the marginal distributions of these risks are known and the task is to quantify their joint effect on a given system. This is typically done by applying a meaningful risk measure to the sum of the individual risks. For this purpose, the stochastic interdependencies between the risks need to be specified. In practice, the models of this dependence structure are however subject to relatively high model ambiguity. The contribution of this paper is twofold: First, we derive a dual representation of the considered problem and prove that strong duality holds. Second, we propose a generally applicable and computationally feasible method, which relies on neural networks, in order to numerically solve the derived dual problem. The latter method is tested on a number of toy examples, before it is finally applied to perform robust risk aggregation in a real‐world instance.     

Neural networks in strategic marketing: exploring the possibilities

A review of the literature indicates that few studies have used artificial neural networks (ANNs) for data analysis in business and marketing research, even though there are many benefits to the use of ANNs. Therefore, this article discusses neural networks (NNs) that can be used in addition to or as an alternative to linear regression for data analysis in strategic marketing. The function and layout of NNs make them ideal for research dealing with nonlinear, incomplete, unspecified, or ‘fuzzy’ data and offer several advantages over linear regression. Unfortunately, in many marketing studies, the information being modeled is far from flawless and is often riddled with ambiguities linear regression is insufficient to accurately assess. NNs could be employed for great benefit by researchers analyzing the nonlinear, complex relationships in business data. The article discusses examples of types of studies that could be strengthened or expanded from neural network use.     

Uncertainty representation and risk management for direct segmented marketing

ABSTRACT

Mining for truly responsive customers has become an integral part of customer portfolio management, and, combined with operational tactics to reach these customers, requires an integrated approach to meeting customer needs that often involves the application of concepts from traditionally distinct fields: marketing, statistics, and operations research. This article brings such concepts together to address customer value and revenue maximisation as well as risk minimisation for direct marketing decision-making problems under uncertainty. We focus on customer lift optimisation given the uncertainty associated with lift estimation models, and develop risk management and operational tools for the multiple treatment (recommendation) problem using stochastic and robust optimisation techniques. Results from numerical experiments are presented to illustrate the effect of incorporating uncertainty on the performance of recommendation models.     

Catch Them If You Can: The Effect of Reminder Direct Mailings on the Return Rate of First-Time Donors

Despite the relevance of interactive marketing strategies, most nonprofit organizations rely on a marketing mix with a focus on direct marketing. Previous research shows that, by optimizing the mailing frequency, organizations are able to distinguish their mailing from other mailings that donors receive. However, some organizations, such as blood services, struggle to convert the frequency recommendations into their marketing practice. As donation events occur irregularly and blood donors are only able to donate a certain number of times, mailing strategies have to result in blood donations. This study examines a strategy in which a reminder direct mailing follows the regular invitation a few days before a particular donation event. A field experiment was conducted with 396 donors; 203 received the double mailing. Surprisingly, the results from hierarchical binary logistic regressions do not reveal any differences between the experimental groups. A single direct mailing approach is recommended, leading to considerable cost savings.     

Artificial Neural Systems as a Research Paradigm for the Study of Group Decision Support Systems

Artificial neural systems (ANSs) have received interest recently because of their ability to accurately forecast and classify data. Group decision support systems (GDSSs) also have received much interest for their support of group communication and decision making. This paper explores the potential of the ANS as a methodology for modeling the many complex, interrelated research variables involved in the field of GDSS. As an illustration, multilinear regression, an ANS with backpropagation, and an ANS with a genetic algorithm were developed to classify 133 subjects into verbal or GDSS groups based on their responses to a questionnaire. The ANSs with backpropagation and the genetic algorithm achieved higher classification accuracies (81.8 and 90.9%, respectively) than was achieved with multilinear regression (75.8%). Therefore, an ANS may more accurately model the many interrelationships occurring with GDSS group behavior.     

International entrepreneurial marketing strategies of MNCs: Bricolage as practiced by marketing managers

The extant research lacks information on entrepreneurial marketing in large international firms. This study explores the international entrepreneurial marketing strategies of multinational corporations (MNCs), and its results reveal that MNC marketing managers use bricolage to develop international entrepreneurial marketing. A novel finding of the study is that the international entrepreneurial marketing strategies of MNCs include co-innovation, accelerating customer value, and international expansion based on regional market leadership. Marketing managers use both parallel and selective bricolage in their international entrepreneurial marketing. Environmental uncertainty and entrepreneurship culture are important drivers of the implementation of bricolage to develop international entrepreneurial marketing. The research findings can inform MNC management of the options available to utilize corporate venturing to facilitate bricolage and in turn to realize international entrepreneurial marketing strategies.     

Virtual influencers as an emerging marketing theory: A systematic literature review

Over the past few years, the popularity of influencers on social media (SM) has increased, and influencer marketing has become an important element in companies' marketing strategies. This has resulted in significant interest from researchers and practitioners; consequently, the number of publications devoted to the topic of influencers and influencer marketing has risen. Simultaneously, computer-generated avatars and virtual influencers (VIs), including those using artificial intelligence (AI) and machine learning, have begun to emerge and gain popularity in the SM space. Thus far, research on these topics has been limited, with few studies examining the issue from different perspectives. Given the growing potential of VIs' inclusion in the consumer decision-making process, and this being a developing field, a comprehensive and critical review of existing research on this subject is urgently needed. In response, this study consolidates the current state of research on virtual, AI, and computer-generated influencers. A systematic review of peer-reviewed articles was conducted to identify key themes and dominant concepts. An analysis of 35 articles provides an understanding of this phenomenon, shedding light on the mechanisms underlying the appeal of VIs and their role in shaping consumer attitudes and behaviors. Based on the analysis, the main thematic streams from the study are presented. Further, research gaps have been identified, and recommendations made for future research directions.     

A Neural Network Classification of Export Success in Japanese Service Firms

Abstract

This study examines the export performance of 350 randomly selected Japanese engineering service firms. Inquiry is made regarding environmental, organizational, managerial, strategic, and functional determinants of these exporting firms. Two primary questions are addressed. Can performance category membership of engineering service exporters be predicted? Second and foremost, which determinants are the most effective in differentiating between the export performance categories? An Artificial Neural Network is selected as the statistical method because of the different perspective it provides for a highly non-linear function having many variables, offering results that consistently prove to numerically approximate such functions much easier than conventional methods, together with the ability to dependably and accurately predict membership classification while providing weighted analyses of input variables. Findings suggest that each group's membership can be consistently and accurately predicted and further identify which determinants dominantly impact category membership as supported by differences in the feature extraction phase of the neural network approach.     

Interdependency factors influencing the World Wide Web as a channel of interactive marketing

The author identifies critical research issues of the interdependencies between the effectiveness of using the World Wide Web as a channel of interactive marketing and factors posed by the limitations of the media, both qualitative and technological. He proposes a model to explain the flow of a transaction in this hypermedia CME and isolates the critical paths in this flow and thier possible effects on the given transaction and isolates the effects to taking alternate routes across those critical paths for a marketer.     

The indirect effects of foreign direct investment on trade: A network perspective

The relationship between international trade and foreign direct investment (FDI) is one of the main features of globalisation. In this paper, we investigate the effects of FDI on trade from a network perspective, since FDI takes not only direct but also indirect channels from origin to destination countries because of firms’ incentive to reduce tax burden, to minimise coordination costs and to break barriers to market entry. We use a unique data set of international corporate control as a measure of stock FDI to construct a corporate control network (CCN), where the nodes are the countries and the edges are the corporate control relationships. Network measures, as the shortest path length and the communicability, are then computed on the CCN to capture the indirect channel of FDI. Empirically, we find that corporate control has a positive effect on trade both directly and indirectly. The result is robust with different specifications and estimation strategies. Hence, our paper provides strong empirical evidence of the indirect effects of FDI on trade. Moreover, we identify a number of interplaying factors such as regional trade agreements and the region of Asia. We also find that the indirect effects are more pronounced for the manufacturing sector than for primary sectors such as oil extraction and agriculture.     

Toward a deeper understanding of service marketing: The past, the present, and the future

The authors investigate the intellectual pillars of service marketing and its evolution through key subareas during 1992-2009 using a citation-based approach. They derive insights for the most promising research directions. The results reveal the dynamic influences of different research topics on service marketing. In a graphical representation, the authors further show that the main topics have changed their research orientations over time. For example, the literature on online service & technology infusion reveals an increasingly operational and customer-focused orientation. A citation-based measure of the significance of research opportunities and a comparison with the topics found in recent literature reviews indicate that research on managing business-to-business services & service infusion, complaint handling & service recovery, and enhancing and managing the service value chain are promising topics. These results assist academics and practitioners by revealing what we know about service research and what we need to know in the future.     

Children and Government Propaganda

Abstract

Around the world “public relations” is confused with “propaganda.” Although “propaganda” has negative connotations today, the authors examine the history of propaganda studies, which is tied to the government-sponsored study of communication. Then they offer a recent example of how the U.S. government used children as messengers of propaganda. By abandoning our prejudices against propaganda, the authors argue we can reconnect public relations with a tradition of scholarship on communication audiences, public communication campaigns, and government propaganda efforts.     

Customer loyalty through social networks: Lessons from Zara on Facebook

Companies’ escalating investment in social media—in particular, in Facebook—has become reality. However, most firms still do not see social networks as a vehicle for cultivating and winning customer loyalty, but rather as a resource for creating brand awareness. In this article, we offer a different view. By examining fans and non-fans of the Zara brand on Facebook, we discovered that Facebook enhances the relations that increase loyalty via trust, customer satisfaction, perceived value, and commitment. Our results revealed that these relations are stronger for fans of the brand than for non-fans, and suggest that customer satisfaction is the strongest determinant of loyalty. This indicates a new opportunity for marketing managers to achieve customer loyalty: Facebook.     

Influencer marketing: Social media influencers as human brands attaching to followers and yielding positive marketing results by fulfilling needs

While the literature related to this topic has predominantly focused on investigating the influence mechanism that social media influencers (SMIs) impose over their followers, less is known about their attachment mechanism. Given that social media platforms were originally designed to facilitate personal bonding and not product or brand recommendations, we posited that social media followers' emotional attachment to SMIs is an important precedent that affects the followers' behavioral inclination to accept the SMIs' endorsements. We thus drew new attention to the relationship between SMIs and their followers by focusing on their attachment development mechanism and its casual factors and effects. In doing so, Study 1 inductively analyzed the key causal factors, both with respect to SMI persona- and content-driven attributes, that make followers feel attached to SMIs. By integrating the findings of Study 1 with the human brand theory, Study 2 provided empirical evidence after analyzing 325 U.S. consumers' responses about how SMIs' personas (i.e., inspiration, enjoyability, and similarity) and content curation abilities (i.e., informativeness) affected followers to perceive the SMIs as human brands who fulfill their needs for ideality, relatedness, and competence—all of which resulted in an intense attachment to SMIs. It was this positive emotion shaped with SMIs that transferred to SMIs’ endorsements and positively influenced the followers to acquire the products/brands that the SMIs recommended.     

分离通道联合卷积神经网络的自动调制识别

针对通信信号的自动调制识别需要大量特征提取的问题,提出了一种分离通道卷积神经网络自动调制识别算法。该算法通过结合深度学习中卷积神经网络(CNN),分别提取时域信号的多通道和分离通道调制特征,再利用融合特征实现不同信号的分类。仿真结果表明,相比基于CNN的算法,所提算法在高信噪比下针对两个数据集的识别率分别提升7%和18%;此外,相比于基于特征提取的传统识别算法,其高阶调制识别性能平均提升3 dB。     

An empirical comparison of neural network and logistic regression models

The purpose of this paper is to critically compare a neural network technique with the established statistical technique of logistic regression for modeling decisions for several marketing situations. In our study, these two modeling techniques were compared using data collected on the decisions by supermarket buyers whether to add a new product to their shelves or not. Our analysis shows that although neural networks offer a possible alternative approach, they have both strengths and weaknesses that must be clearly understood.     

E-loyalty driven by website quality: The case of destination marketing organization websites

The capability of website quality management to drive tourism customer e-loyalty is the key factor to achieve superior performance of destination marketing organization (DMO) website operations. The quality management approaches that revolve around website design quality and online relationship quality have drawn intensive attention from e-loyalty researchers in recent years. Thorough empirical investigation, however, still lacks in incorporating the integrative impact generated by the two approaches into DMO website quality management. The current study introduces and validates a theoretical framework based on such impact. As the research result reveals, six facets predict tourism customer e-loyalty directly: informational usefulness, navigational effectiveness, aesthetic appeal, entertainment, social presence, and self-concept congruity embedded in the functional, emotional, and symbolic dimensions of website design quality. Online relationship quality, comprised of relationship satisfaction and relationship trust, plays a partial mediator role in amplifying the e-loyalty driving effect of website design quality in the DMO website context.