Francis J. Mulhern

Customer profitability analysis: Measurement, concentration, and research directions

Abstract As marketing activities become more precisely targeted to consumers through direct and interactive forms of communication, customer profitability takes on a central role in the development of marketing strategies. This paper provides a conceptual and methodological foundation for measuring customer profitability by generalizing approaches to measuring customer lifetime value in direct marketing for broader target marketing applications. Particular emphasis is placed on the precise specification of the inputs into a profitability analysis and the measures of the degree of concentration of profits among customers. An empirical analysis involving the profitability of customers in a business-to-business marketing context is described, along with research propositions for future work on the determinants of customer profitability.

Retail marketing: From distribution to integration

Abstract Retailing represents the culmination of the marketing process, the contact point between consumers and manufacture products, marketing communications and customer service. This paper reviews the research on retail marketing that has appeared in the academic literature in the last several years. The review will address the revolutionary changes occurring in retailing today brought on by the availability of purchase transaction databases and new forms of marketing communications. The author suggests a reorientation of the role of retailers away from the prevailing focus on distribution toward an emphasis on integrated communications and the management of customer relationships. Research on many aspects of both store and nonstore retailing are discussed in terms of this orientation.

Variability of brand price elasticities across retail stores: Ethnic, income, and brand determinants

Abstract Retail pricing decisions are often made with respect to the price sensitivity of shoppers in a retail store or market area. This paper explores how certain brand and consumer characteristics relate to the variability of brand price elasticities across stores belonging to the same chain. The authors measure the price sensitivity of 14 liquor brands sold in 35 store locations. Since the stores operate in a monopoly environment, the analysis is free from the confounds caused by competitive pricing or promotional activity that often hamper retail pricing studies. Also, the monopoly situation provides data that represent a census of brand sales in the categories studied. Results of a two-stage econometric analysis show that brand price elasticity is higher for brands that are promoted more frequently and for brands that have higher market shares. The magnitude of brand price elasticity is also found to be directly related to the household income in a market area and inversely related to the proportion of residents in a market area who are African-American.

Retail promotional advertising: Do the number of deal items and size of deal discounts affect store performance?

Abstract Retailers use advertised price promotions to attract customers and stimulate store traffic and sales. While several studies have investigated the efficacy of individual-brand promotions, little empirical research has investigated the ways in which store-level promotion strategies influence retail performance. This article reports on a natural experiment involving a change in a grocery stores promotion strategy from featuring many items at small discounts, to a few items at deep discounts. Results of a time series intervention analysis indicate that such a change in strategy led to an increase in chain-level sales dollars but did not affect customer traffic.

A comparative analysis of shopping behavior in Hispanic and non-Hispanic market areas

Abstract Many retailers target shoppers belonging to ethnic minorities, particularly Hispanics. Most often, ethnic oriented retailing involves specialized marketing efforts in retail stores located in market areas with high concentrations of ethnic consumers. Previous research, through respondent self-reports, has attempted to determine how Hispanic shopping behavior differs from that of other customer groups. However, past studies have not investigated actual purchase behavior in stores located in ethnically concentrated market areas. Drawing on past research, we develop and test several hypothesis about shopping behavior in Hispanic market areas. Results show that shoppers in Hispanic trading areas are comparable to shoppers in non-Hispanic areas with respect to direct price responsiveness and brand substitution. However, we find that store brand purchasing is more prevalent in market areas with high concentrations of Hispanics.

A nearest neighbor model for forecasting market response

Abstract Researchers in marketing often are interested in modeling time series and causal relationships simultaneously. The prevailing approach to doing so is a transfer function model that combines a Box-Jenkins model with regression analysis. The Box-Jenkins component assumes that a stationary, stochastic process generates each data point in the time series. We introduce a multivariate methodology that uses a nearest neighbor technique to represent time series behavior that is complex and nonstationary. This methodology represents a deterministic approach to modeling a time series as a discrete dynamic system. In this paper we describe how a time series may exhibit chaotic behavior, and present a multivariate nearest neighbor method capable of representing such behavior. We provide an empirical demonstration using store scanner data for a consumer packaged good.

The Advertising Exposure Effect of Free Standing Inserts

Abstract Manufacturers of consumer packaged goods regularly distribute coupons through free standing inserts in newspapers. In this paper, we investigate the possibility that free standing inserts have an advertising exposure effect that influences the brand purchases of shoppers who do not use coupons in the category studied. If free standing inserts for a brand do have a pure advertising exposure effect, there should be an increase in the sales of that brand even to non-users of the coupons. Results of an empirical analysis show that such an effect does exist for two of the six cases investigated. We also find some evidence of a cross-brand advertising exposure effect indicating that the sales of a competing brand to non-users of coupons decrease in the weeks following the appearance of a coupon in a free standing insert.

Measuring market response to price changes: A classification approach

Abstract In making pricing decisions, marketing managers frequently change prices concurrently with other marketing mix variables. In order to assess market response to such changes, managers must measure the overall effect of changes in multiple marketing variables. The authors describe an approach for evaluating the interaction effect of multiple marketing variables by searching a historical database for instances in the past where similar changes took place. Market response can be assessed by evaluating how markets responded to these similar changes in the past. An empirical example is provided to demonstrate how managers can predict market response to future price changes using information on past market response contained in large scanner databases.

Estimating individual cross-section coefficients from the random coefficient regression model

Marketing researchers frequently encounter cross-sectional, time-series data when developing sales response models. One approach to analyzing such data is to estimate a separate OLS equation for each cross-section. Alternatively, one could pool the data from all cross-sections to estimate a single set of response coefficients for all cross-sections. However, when data are pooled, the responsiveness of individual cross-sections cannot be evaluated. In this note, we introduce a version of the random coefficient model that can be used to estimate separate sets of response coefficients for each cross-section, thereby circumventing the assumption that coefficients are homogeneous in all cross-sections. We demonstrate this approach with an empirical model that relates brand level sales to price and advertising.