Journal of Retailing and Consumer Services 10 (2003) 121–122
Editorial
Special Issue on Model Building in Retailing and Consumer Services The main goal of this special issue is to stimulate thought, reflection and action about important issues, facets, methods, approaches, applications and managerial implications, related to the whole spectrum of model building when applied to the specific cases of retailing and consumer services domains. One of its critical features is that the researchers look beyond the current state of knowledge to consider evolving issues and expected directions of change that will influence the thought and practice related to management model building and its future uses. Retail managers have been interested in learning about the cross-category purchase behaviour of their customers for a fairly long time. More recently, the task of inferring cross-category relationship patterns among retail assortments is gaining attention due to its promotional potential within recommended systems used in online environments. Collaborative filtering algorithms are frequently used in such settings for the prediction of choices, preferences and/or ratings of online users. Mild and Reutterer investigate, in the first article of this special issue, the suitability of such methods for situations when only binary pick-any customer information (i.e., choice/non-choice of items, such as shopping basket data) is available. They introduce an extension of collaborative filtering algorithms for such data situations and apply it to a real-world retail transaction data set. The new method is benchmarked against more conventional algorithms and can be shown to deliver superior results in terms of predictive accuracy. Prior segmentation research has primarily focused on market behaviour, lifestyle and socio-demographics rather than on purchase histories. In the second article of this special issue, Joh, Timmermans and Popkowski-Leszczyck propose the use of sequence alignment methods (SAM) to segment customers based on their purchase histories. The principles underlying the method are introduced, and the method is illustrated by the authors through the use of scanner panel data. Their results suggest that, compared to the conventional methods, the proposed technique results in a better segment solution that captures both the shopping frequency and varietyseeking information. The findings of this study have
important implications for differentiation and market positioning strategies. In the next article by Hay, Wets and Vanhoof, the SAM is employed for segmentation of visiting patterns on a web site. Instead of clustering users by means of a Euclidean distance measure, in their approach, users are partitioned into clusters using a non-Euclidean distance measure. This method ensures that sequential relationships, represented by the order of elements, are taken into account. In experiments using real traffic data on the web site of a Belgian telecom provider, the performance of SAM is compared with the results of a method based on Euclidean distance measures. Empirical results show that SAM identified segments presenting behavioural characteristics not only with regard to content but also considering the order of pages that are visited on a web site. Traditionally, firms use intermediaries to reach final consumers. More recently some companies have chosen to rely exclusively on direct channels, bypassing all forms of intermediaries (e.g. Internet retailers). In the next article, Park and Keh look at the firm’s decision making when hybrid channels exist (where the company uses both direct and indirect channels). Using game theory, they compare the equilibria under the indirect and vertically integrated channels with the equilibrium under the hybrid channel with respect to the marketing decision variables, particularly pricing and profit distribution. Some results are quite surprising and set up the benchmark comparisons for future work in this area. A model of consumer’s choice between different supermarket formats was developed by Solgaard and Hansen, and is presented in the next article of this issue. Three formats are considered, conventional supermarkets characterised by high-low pricing wide assortment and some service, discount stores characterised by everyday-low-pricing, narrow assortment and no service, and hypermarkets, characterised by a pricing policy somewhat in between the two other formats, large assortment and some service. The model is developed within the framework of the multinomial logit model that has been widely used in retailing but also strongly criticised. Problems involved in using this framework are discussed, and a random coefficients logit model is suggested to remedy these problems. The model is
0969-6989/03/$ - see front matter r 2003 Elsevier Science Ltd. All rights reserved. doi:10.1016/S0969-6989(03)00002-X
122
Editorial / Journal of Retailing and Consumer Services 10 (2003) 121–122
estimated as a hierarchical Bayes model, and the estimated parameters are compared to the estimates of a standard logit model. The importance of the choice determinants is assessed by analysing direct and cross choice elasticities. And finally, the last article included in this special issue on ‘‘Model Building in Retailing and Consumer Services’’ deals with the implementation of Customer Relationship Management (CRM) systems for online retailing. In the highly competitive digital market, the development of a CRM strategy may represent the difference between success and failure for online retailing firms. The restructuring of the business system is extremely complex in the digital environment, requiring careful planning, modelling and implementation of a customer-oriented approach. In this paper, Wilcox and Gur*au identify and analyse the main advantages of the Unified Modelling Language (UML) for business modelling, presenting as a general example the case of the implementation of a CRM strategy for online retailing companies. It is clear that corporate management needs a wide range of relevant strategic and operational information, domain knowledge, and assistance with robust analytical frameworks and models in order to overcome inherent limitations and shortcomings in the process of making near-accurate decisions. It is also believed that these needs can be met, to a great extent, by suitable uses of model-building procedures and techniques. All the authors have made an important contribution to this specific field of scientific research. We sincerely appreciate the opportunity to work with this group of academic peers. We are confident that these articles will encourage a continuing dialogue and motivation for research concerning model building in retailing and consumer services. Finally, we would like to thank Sylvia Kerrigan for the great deal of help given to us in putting together the final version of the Special Issue and for being the ‘‘lifeline’’ with the contributors, reviewers as well as between the two editors. We would also like to thank all the academics and contributors who have submitted papers to this special issue for their understanding with some of the more lengthy stages associated with the reviewing process. Furthermore, we would also like to show our gratitude to Harry Timmermans for all the demonstrated support, confidence and patience. We both hope you enjoy reading the articles.
We should like to thank the reviewers for this Special Issue: Malcolm Beynon Cardiff University, Wales Gerrit van Bruggen Rotterdam School of Management, The Netherlands Margarida Cardoso University of Lisbon, Portugal Michael Hahsler Vienna University of Economics and Business Administration, Austria Kurt Hornik Vienna University of Technology, Austria Harald Hruschka University of Regensburg, Germany Graeme D Hutcheson University of Manchester, England Gustaf Neumann Vienna University of Economics and Business Administration, Austria Thomas Otter University of California, Riverside, USA Thomas Reutterer Vienna University of Economics and Business Administration, Austria Gary J. Russell University of Iowa, Iowa City, USA Peter Schnedlitz Vienna University of Economics and Business Administration, Austria Kalpana Scholtes-Dash Institute for Advanced Studies, Vienna, Austria Geoff Southern University of Glasgow, Scotland Jerzy Stefanowski Poznan University of Technology, Poland Niko Tzokas University of East Anglia, England
a
L. Moutinhoa Department of Management Studies Business School University of Glasgow, West Quadrangle Gilbert Scott Building, Glasgow G12 8QQ, UK E-mail address:
[email protected] b
J. Mazanecb Vienna University of Economics and Business Administration, Austria