Suchergebnisse

AbstractThis paper proposes a new model of consideration set sizes, which relies on a stochastic modelling approach to better understand data patterns. The paper combines the Poisson distribution with the lognormal distribution proposed by Hauser and Wernerfelt (1990) to create the Poisson lognormal (PLN) model of consideration set sizes. An advantage of PLN is that it allows variance within a given individual consumer. This is a crucial factor for brand managers who wish to choose a particular market to promote their brand, as a higher within‐individual variance suggests that there is more chance for a consumer to change their consideration set size, whereas a lower within‐individual variance indicates that a consumer tends to stick to his/her consideration set size. The paper then uses 10 datasets including service, durable and fast‐moving consumer goods across four countries to validate the new model and compare it with the lognormal model. The results show that PLN gives a good fit to these data. It outperforms the lognormal model. The average mean absolute percentage error of the PLN model is 12 per cent, whereas that of the lognormal model is 26 per cent. For managerial implications, the paper proposes a better tool to help brand managers analyse the nature and intensity of competition that is facing their brands. Also, relying on its stochastic element, the proposed model can help brand managers predict future brand consideration by their consumers, as well as evaluate any change in brand consideration, caused by marketing activity such as sales promotion and advertising. Copyright © 2014 John Wiley & Sons, Ltd.

This paper proposes and validates the negative binomial distribution (NBD) to predict the variation in repertoire size (the number of brands purchased by a consumer in a specific time period) within a category. From a managerial perspective, the variation is crucial for brand managers who would like to know the nature and intensity of competition that is facing their brands. Empirical findings across multiple datasets from UK consumer packaged goods demonstrate that the NBD model predicts variations in repertoire size very well in different time periods (1year, 18months and 3years), and different buyer groups (light and heavy category buyers). The paper then suggests a simple method to predict those who are brand exclusively loyal, those who are loyal to a few brands, and those who are diversified to buy multiple brands, based on very little information such as category and brand penetrations, using the parameters of the NBD model.

AbstractE‐fashion brand competition has historically been studied from an attitudinal lens, through surveys and theory‐based approaches. These studies generally examine consumer attitudes, satisfaction and loyalty; highlighting that trust, satisfaction and reputation are key e‐commerce success elements. However, the empirical consumer behaviour literature rebuts the use of attitudes to explain brand performance, criticising their subjectivity and the overall ineffectiveness of loyalty as a brand growth tool. The article presents Gerald Goodhardt and colleagues' Dirichlet model as an alternative approach to understanding e‐fashion buyer behaviour. The Dirichlet model is a robust, stochastic model that has reliably predicted well‐established law‐like patterns of buyer behaviour and brand competition. We apply Dirichlet modelling to a new, non‐fast moving consumer goods category to extend consumer behaviour research in the online environment. The study uses consumer panel data from the United Kingdom, across two consecutive years. We conclude that the Dirichlet model has an excellent fit within the eBay fashion brand market. The study also identifies that the well‐known double jeopardy pattern exists within this market, demonstrating that e‐fashion brands grow through acquisition rather than retention of customers. This provides a different viewpoint than most e‐fashion brand growth literature. In addition to this, we examine the predictive capability of the Dirichlet model. We use a holdout sample to show that the model can predict future brand performance metrics, which is an exciting new development in consumer behaviour research.

AbstractUltra‐light buyers, those who, on average, buy a brand once a year or less, are important by number and their contribution to brand purchase occasions. The initial research, however, was limited in scope and did not measure the contribution of these buyers to sales volume or value. By examining over 850 brands in almost 60 categories, we identify that ultra‐lights make up 62% of a brand's buyer base over 5 years and contribute 32% of purchase occasions and 31% of sales volume and value. In line with previous findings that brands with higher loyalty exhibit more repeat purchases and thus fewer ultra‐light buyers and private label brands often exhibit higher than expected loyalty for their market share—we find the prevalence of ultra‐light buyers is higher for national brands than private labels, likely reflecting the higher loyalty often observed for private labels. We also find no difference in ultra‐light buyers' contribution between high and low‐price brands, indicating that price is not a significant factor affecting the contribution of ultra‐light buyers. Finally, we find that both growing and declining brands have fewer ultra‐lights than stable brands. As growth occurs via increasing penetration and loyalty, for growing brands, new buyers may be more 'light' than 'ultra‐light' in terms of their loyalty; while for declines, these findings imply that there are not enough ultra‐light buyers to maintain brand sales. A failure to recruit ultra‐light buyers may be very dangerous for brand health.

Purpose
This paper aims to extend the known boundary conditions of the negative binomial distribution (NBD) model, and to test the applicability of conditional trend analysis (CTA) – a key method to identify whether changes in overall sales are accounted for by previous non-buyers, light buyers or heavy buyers – in industrial purchasing situations.


Design/methodology/approach
The study tested the NBD model and CTA in an industrial marketing context using a 12-month data set of purchases from an Australian supplier of a range of industrial plastic resins.


Findings
The purchase data displayed a good NBD fit; the study therefore extends the known boundary conditions of the model. The application of CTA provided second-period purchasing frequency estimates showing no significant difference from actual data, indicating the applicability of this method to industrial purchasing.


Research limitations/implications
Data relate to just one supplier. Further research across several industries is required to confirm the generalizability and robustness of NBD and CTA to industrial markets.


Practical implications
Marketing decisions can be improved through appropriate analysis of customer purchasing data. However, without access to equivalent competitor data, industrial marketers are constrained in benchmarking the purchasing patterns of their own customers. The results indicate that use of the NBD model enables valid benchmarking for industrial products, while CTA would enable appropriate analysis of purchases by different classes of customer.


Originality/value
This paper extends the known boundary conditions of the NBD model and provides the first published results, indicating the appropriateness of CTA to predict purchasing frequencies of different industrial customer classes.

AbstractMarketers are interested in the loyalty of their customer base. Increasingly this includes examining behavioural loyalty inferred from the frequency or weight of purchase. A typical approach is to divide the customer base into arbitrary segments based on weight of purchase and then attempt to move customers from lighter to heavier segments, rather than have them reduce purchasing or cease buying altogether. Effects can be monitored by examining how purchasing by groups of individuals evolves over successive periods. However, much of the flow between segments represents random fluctuations in period‐to‐period purchasing rather than true change to underlying loyalty. Accurate analysis requires true change to be separated from these stochastic changes, for example through benchmarks derived from conditional trend analysis (CTA). While CTA considers the two‐period case, it provides no guidance for changes seen across three‐periods. The three‐period case is nonetheless regularly reported by panel companies and relied on by managers. We therefore develop the three‐period CTA, using a tri‐variate NBD, to allow the analysis of buyer flow across three successive periods. We provide an empirical illustration and demonstrate fresh insights into the evolution of consumer loyalty. The findings allay oft‐raised concerns about supposedly 'lost' buyers, as perceived customer loss is often simply regression to the mean of the buying rates. Accordingly, the three‐period CTA shows predictable proportions of buyers who move between different buying‐weight segments, including first‐year buyers who were apparently 'lost' in the second year but return to buy the brand in the third year.