Thomas Reutterer

An improved collaborative filtering approach for predicting cross-category purchases based on binary market basket data

Retail managers have been interested in learning about cross-category purchase behavior of their customers for a fairly long time. More recently, the task of inferring cross-category relationship patterns among retail assortments is gaining attraction due to its promotional potential within recommender 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. This paper investigates the suitability of such methods for situations when only binary pick-any customer information (i.e., choice/nonchoice of items, such as shopping basket data) is available. We present an extension of collaborative filtering algorithms for such data situations and apply it to a real-world retail transaction dataset. The new method is benchmarked against more conventional algorithms and can be shown to deliver superior results in terms of predictive accuracy. (authors abstract)

Store format choice and shopping trip types

Purpose – The purpose of the paper is to identify store format attributes that impact on store format choice when consumers conduct fill‐in or major trips to buy groceries. By doing so, we take into consideration that consumers patronise multiple (store based) formats depending on the shopping situation operationalised by the type of shopping trip.Design/methodology/approach – The paper adopts the conceptual framework of random utility theory via application of a multinomial logit modelling framework. The analysis is based on a survey of 408 consumers representing households in a clearly defined central European retail area.Findings – The results reveal a considerable moderating effect of the shopping situation on the relationship between perceived store format attributes and store format choice. Consumers utilities are significantly higher for discount stores and hypermarkets when conducting major trips. To the contrary, supermarkets are preferred for fill‐in trips in the focussed retail market. Merchan...

The Use of Conjoint-Analysis for Measuring Preferences in Supply Chain Design

Abstract In this paper we introduce the methodology of conjoint-analysis as an appropriate tool to evaluate the preferences and expectations of supply chain managers in designing a supply chain. Our study is based on 41 personal interviews, conducted among Austrian supply chain managers. Due to the considerable heterogeneity of the sample respondents, the assumption of a single “correct” supply chain design appears doubtful. According to our results four different types of supply chain designs were derived. In conclusion, the use of conjoint-analysis offers a promising tool to generate information in the way logistics managers design different versions of supply chains.

Hedonic and Utilitarian Shopper Types in Evolved and Created Retail Agglomerations

This paper focuses on the impact of hedonic and utilitarian values of shopping on retail agglomeration patronage issues, in particular on shopping behaviour and the perception of retail agglomerations. Our empirical study is based on a discussion of agglomerations potential to attract utilitarian and hedonic shopper types. A sample of 2,139 customers were interviewed in a peripheral shopping mall as well as on an inner city shopping street and confronted with a multi-item scale operationalising shopping values as developed by Babin, Darden and Griffin (1994). Using a standard fuzzy c-means clustering algorithm we identified four distinct shopper types. The results show that hedonists are represented by a higher number of females, earn lower individual incomes and are less educated compared to utilitarians. A higher share of hedonists visited the shopping mall. Overall, they make more shopping trips to agglomerations, stay there longer, visit more stores and–depending on the agglomeration format–spend less than or the same amount as utilitarians. Finally, we see that those customers who are attracted by agglomerations because of atmospheric and price stimuli are typical hedonists.

Geographical Information Systems-Based Marketing Decisions: Effects of Alternative Visualizations on Decision Quality.

Marketing planners often use geographical information systems (GISs) to help identify suitable retail locations, regionally distribute advertising campaigns, and target direct marketing activities. Geographical information systems thematic maps facilitate the visual assessment of map regions. A broad set of alternative symbolizations, such as circles, bars, or shading, can be used to visually represent quantitative geospatial data on such maps. However, there is little knowledge on which kind of symbolization is the most adequate in which problem situation. In a large-scale experimental study, the authors show that the type of symbolization strongly influences decision performance. The findings indicate that graduated circles are appropriate symbolizations for geographical information systems thematic maps, and their successful utilization seems to be virtually independent of personal characteristics, such as spatial ability and map experience. This makes circle symbolizations particularly suitable for effective decision making and cross-functional communication.

Implications of Probabilistic Data Modeling for Mining Association Rules

Mining association rules is an important technique for discovering meaningful patterns in transaction databases. In the current literature, the properties of algorithms to mine association rules are discussed in great detail. We present a simple probabilistic framework for transaction data which can be used to simulate transaction data when no associations are present. We use such data and a real-world grocery database to explore the behavior of confidence and lift, two popular interest measures used for rule mining. The results show that confidence is systematically influenced by the frequency of the items in the left-hand-side of rules and that lift performs poorly to filter random noise in transaction data. The probabilistic data modeling approach presented in this paper not only is a valuable framework to analyze interest measures but also provides a starting point for further research to develop new interest measures which are based on statistical tests and geared towards the specific properties of transaction data.

A combined approach for segment-specific market basket analysis

Abstract Market baskets arise from consumers’ shopping trips and include items from multiple categories that are frequently chosen interdependently from each other. Explanatory models of multicategory choice behavior explicitly allow for such category purchase dependencies. They typically estimate own and across-category effects of marketing-mix variables on purchase incidences for a predefined set of product categories. Because of analytical restrictions, however, multicategory choice models can only handle a small number of categories. Hence, for large retail assortments, the issue emerges of how to determine the composition of shopping baskets with a meaningful selection of categories. Traditionally, this is resolved by managerial intuition. In this article, we combine multicategory choice models with a data-driven approach for basket selection. The proposed procedure also accounts for customer heterogeneity and thus can serve as a viable tool for designing target marketing programs. A data compression step first derives a set of basket prototypes which are representative for classes of market baskets with internally more distinctive (complementary) cross-category interdependencies and are responsible for the segmentation of households. In a second step, segment-specific cross-category effects are estimated for suitably selected categories using a multivariate logistic modeling framework. In an empirical illustration, significant differences in cross-effects and price elasticities can be shown both across segments and compared to the aggregate model.

A nonparametric approach to perceptions-based market segmentation : applications

How tourists perceive city destinations - a case for perceptions-based market segmentation and competition analysis (S. Dolnicar): The need for strategic marketing research Data Answer pattern compression Perceptual competition analysis Concentration analysis Segment formation Conclusions.- Segmentation and positioning analysis of competitive retail markets based on binary store image and preference data (C. Buchta, T. Reutterer): Introduction A stepwise segmentation procedure Standard market research data Compression of perceptual profiles Characterizing perceptual classes Formation of market segments Target marketing strategies Discussion.

Collaborative Filtering Methods for Binary Market Basket Data Analysis

Retail managers have been interested in learning about cross-category purchase behavior of their customers for a fairly long time. More recently, the task of inferring cross-category relationship patterns among retail assortments is gaining attraction due to its promotional potential within recommender 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. The fundamental assumption of such algorithms resides in the available similarity information between a specific active user and a database of all other users. We study the effects of different similarity measures, available data points per user and the number of items to be recommended on the relative predictive performance in an experiment using market basket data collected from a grocery retailer. Using various measures for evaluation of the predictive ability, we derive some clues to the proper parameterization of such systems.

Segmentation-based competitive analysis with MULTICLUS and topology representing networks

Abstract Two neural network approaches, Kohonens self-organizing (feature) map (SOM) and the topology representing network (TRN) of Martinetz and Schulten are employed in the context of competitive market structuring and segmentation analysis. In an empirical study using brands preferences derived from household panel data, we compare the SOM and TRN approach to MULTICLUS, a parametric latent vector multi-dimensional scaling (MDS) model approach which also simultaneously solves the market structuring and segmentation problem. Our empirical analysis shows several benefits and shortcomings of the three methodologies under investigation. As compared to MULTICLUS, we find that the non-parametric neural network approaches show a higher robustness against any kind of data preprocessing and a higher stability of partitioning results. As compared to SOM, we find advantages of TRN which uses a more flexible concept of adjacency structure. In TRN, no rigid grid of units must be prespecified. A further advantage of TRN lies in the possibility to exploit the information of the neighborhood graph for adjacent prototypes which supports ex-post decisions about the segment configuration at both the micro and the macro level. However, SOM and TRN also have some drawbacks as compared to MULTICLUS. The network approaches are, for instance, not directly accessible to inferential statistics. Our empirical study indicates that especially TRN may represent a useful expansion of the marketing analysts tool box. Scope and purpose Determination of competitive market structure among rival brands and market segmentation represent well-known concepts in strategic marketing planning. During the last decade, approaches that combine the two interrelated tasks into one single model have been introduced into marketing literature. Most of them respect consumer heterogeneity by including ‘fixed’ parameters (e.g., demographic or past purchase behavior variables) for each individual or by assuming consumer parameters to be distributed according to a (mixture of) probability distribution(s). However, the key to the success of these statistical modeling approaches seems to lie in the proper choice of parametric model assumptions and/or heterogeneity distributions. Due to its non-parametric nature, the neuro-computing methodology presented in this article imposes less rigorous assumptions on data properties and derives segment-specific patterns of competitive relationships between brands in a purely data-driven way.