K. Sudhir

Forecasting Marketing Mix Responsiveness for New Products

Before a new product launch, marketers need to infer how demand will respond to various levels of marketing-mix variables to set an appropriate marketing plan. A critical challenge in estimating marketing-mix responsiveness from historical data is that the observed decisions were affected by private information possessed by managers about the heterogeneous effects of marketing-mix variables on sales. The authors refer to this as the “slope endogeneity” problem. Such endogeneity differs from the “intercept endogeneity” problem, which has been widely acknowledged in the literature. To correct for the slope endogeneity bias, the authors develop a conceptually simple control function approach that is amenable to multiple endogenous variables and marketing-mix carryover effects. The method is applied to forecasting advertising responsiveness in the U.S. DVD market. The results suggest that advertising responsiveness varies substantially across DVD titles and that estimated marketing-mix elasticities would be biased if the slope endogeneity problem were ignored. This analysis also yields findings of substantive interest to researchers and managers involved in entertainment marketing.

The Temporal and Spatial Dimensions of Price Search: Insights from Matching Household Survey and Purchase Data

Price promotions are pervasive in grocery markets. A household can respond to price promotions by effectively cherry-picking through (1) spatial price search across stores and (2) temporal price search across time. However, extant research has analyzed these two dimensions of price search only separately and therefore underestimates both the consumer response to price promotions and the impact of promotions on retail profit. In this article, the authors introduce an integrated analysis of spatial and temporal price search. They seek answers to three questions: First, what are the predictors of household decisions to perform either spatial or temporal price search? Second, how effective are the temporal, spatial, and spatiotemporal price search strategies in obtaining lower prices? and Third, what is the impact of alternative price search strategies on retailer profit? The authors use a unique data collection approach that combines household surveys with observed purchase data to address these questions. Their key results are as follows: Geography (the spatial configuration of store and household locations) and opportunity costs are useful predictors of a households price search pattern. Households that claim to search spatiotemporally avail approximately three-quarters of the available savings on average. Households that search only temporally save about the same as those that search only spatially. The negative effect of cherry-picking on retailer profits is not as high as is typically believed.

Do Bonuses Enhance Sales Productivity? A Dynamic Structural Analysis of Bonus-Based Compensation Plans

We estimate a dynamic structural model of sales force response to a bonus-based compensation plan. This paper provides substantive insight into how different elements of the compensation plan enhance productivity. We find evidence that 1 bonuses enhance productivity across all segments; 2 overachievement commissions help sustain the high productivity of the best performers, even after attaining quotas; and 3 quarterly bonuses help improve performance of the weak performers by serving as pacers to keep the sales force on track in achieving its annual sales quotas. The paper also introduces two main methodological innovations to the marketing literature: First, we implement empirically the method proposed by Arcidiacono and Miller [Arcidiacono P, Miller RA 2011 Conditional choice probability estimation of dynamic discrete choice models with unobserved heterogeneity. Econometrica 796:1823--1867] to accommodate unobserved latent-class heterogeneity using a computationally light two-step estimator. Second, we illustrate how discount factors can be estimated in a dynamic structural model using field data through a combination of 1 an exclusion restriction separating current and future payoff and 2 a finite-horizon model in which there is no forward-looking behavior in the last period.

Optimal marketing strategies for a customer data intermediary

Advances in data collection and storage technologies have given rise to the customer data intermediary (CDI), a firm that collects customer data to offer customer-specific marketing services to marketers. With widespread adoption of customer relationship management (CRM) and one-to-one (1:1) marketing, the demand for such services continues to grow. Extant empirical research using customer data for CRM and 1:1 marketing tends to have an engineering emphasis and focuses on developing analysis techniques to implement CRM and 1:1 marketing optimally (i.e., the technology for the CDI). In contrast, this article focuses on marketing strategy issues that the intermediary faces, given the availability of the technology to implement such services. Specifically, the authors develop an empirical framework to evaluate the optimal customer (exclusive/nonexclusive), product (quality or accuracy of the 1:1 customization), and pricing strategy for a CDI. They illustrate the framework for one type of CDI—a 1:1 coupon service firm that caters to grocery manufacturers—using household purchase history data from the ketchup market. The authors find that selling on a nonexclusive basis using the maximum available purchase history data is the most profitable strategy for the CDI in the particular market. They also evaluate the potential impact of retailers entering the 1:1 coupon service business. Because 1:1 marketing can increase the retailers profits from goods sold, it is optimal for the retailer to undercut the prices of a pure-play CDI that offers 1:1 coupon services.

Do Private Labels Increase Retailer Bargaining Power

Like any new product, private label entry increases competition within a category leading to downward pressure on both wholesale and retail prices. But, given the higher margins for private labels and potential bargaining benefits for retailers, they have incentives to help private labels gain market share. The paper addresses two questions: First, do private labels enhance a retailer’s bargaining power with respect to manufacturers? Second, given the higher profitability and potential increase in bargaining power, does the retailer strategically set retail prices to favor and strengthen the private label? We find support for the “bargaining power” hypothesis, but qualified support for the “strategic retailer pricing” hypothesis. Retailers gain bargaining power through lower wholesale prices on imitated national brands. But the gain is greater in niche categories than in mass categories, suggesting that niche national brands with limited “pull” power lose greater bargaining power. In terms of strategic pricing, the retailer, on initially introducing the private label, strategically sets prices to help private labels gain market share in high volume mass market categories. But retail prices revert to the category profit maximizing price after a year when the private label gains a stable market share.

Do slotting allowances enhance efficiency or hinder competition

Slotting allowances are lump-sum payments by manufacturers to retailers for stocking new products. The economic rationale for slotting allowances is controversial. Supporters argue that slotting allowances are efficiency enhancing; critics argue that they are anticompetitive. However, there is no empirical research on this issue because of the difficulty in obtaining data about these transactions. Using data on all new products that were offered to one retailer for a period of nine months, the authors empirically investigate support for the alternative rationales for slotting allowances. The analysis indicates that, in general, there is more support for the efficiency theories than for the anticompetitive theories. The authors find that slotting allowances (1) efficiently allocate scarce retail shelf space, (2) help balance the risk of new product failure between manufacturers and retailers, (3) help manufacturers signal private information about potential success of new products, and (4) widen retail distribution for manufacturers by mitigating retail competition. The authors find little support for the anticompetitive rationales in the data. The empirical support for the efficiency rationales suggests that the Federal Trade Commission was correct in being circumspect about banning slotting allowances outright.

Bounded Rationality in Pricing Under State-Dependent Demand: Do Firms Look Ahead, and if So, How Far?

The authors propose an empirical procedure to investigate the pricing behavior of manufacturers and retailers in the presence of state-dependent demand. Rather than assuming that firms are perfectly forward looking and therefore solving accordingly for dynamic equilibriums that would arise in the presence of state dependence, the authors systematically evaluate whether boundedly rational firms indeed look ahead when they set prices and, if so, to what extent. They illustrate the procedure using household-level scanner-panel data on breakfast cereals and replicate the substantive results using data on ketchup. The authors find that (1) omission of state dependence in demand biases inference of firm behavior (i.e., tacit collusion is erroneously inferred when firms are competitive); (2) observed retail prices are consistent with a pricing model in which both manufacturers and retailers are forward looking (i.e., they incorporate the effects of their current prices on their future profits), but firms have short time horizons when setting prices (i.e., they look ahead by only one period, suggesting that firms are boundedly rational in their dynamic pricing behavior); and (3) even a myopic pricing model of firms that accounts for state dependence in demand is a reasonable approximation of the observed prices in the market.

Structural Applications of the Discrete Choice Model

A growing body of empirical literature uses structurally-derived economic models to study the nature of competition and to measure explicitly the economic impact of strategic policies. While several approaches have been proposed, the discrete choice demand system has experienced wide usage. The heterogeneous, or “mixed”, logit in particular has been widely applied due to its parsimonious structure and its ability to capture flexibly substitution patterns for a large number of differentiated products.We outline the derivation of the heterogeneous logit demand system. We then present a number of applications of such models to various data sources. Finally, we conclude with a discussion of directions for future research in this area.

When to “Fire” Customers: Customer Cost-Based Pricing

The widespread adoption of activity-based costing enables firms to allocate common service costs to each customer, allowing for precise measurement of both the cost to serve a particular customer and the customers profitability. In this paper, we investigate how pricing strategies based on customer cost information affects a firms customer acquisition and retention dynamics, and ultimately its profit, using a two-period monopoly model with high-and low-cost customer segments. Although past purchase and cost information helps firms to increase profits through differential prices for good and bad customers in the second period (“price discrimination effect”), it can hurt firms because strategic forward-looking consumers may delay purchases to avoid higher future prices (“ratchet effect”). We find that when the customer cost heterogeneity is sufficiently large, it is optimal for firms to “fire” some of its high-cost customers, and customer cost-based pricing is profitable. Surprisingly, it is optimal to fire even some profitable customers. This result is robust even when the cost to serve is endogenous and determined by the consumers choice of service level. We also shed insight on acquisition--retention dynamics, on when firms can improve their profitability by selectively firing known old “bad” customers, and on replacing the old “bad” customers with a mix of new “good” and “bad” customers. This paper was accepted by J. Miguel Villas-Boas, marketing.

Commentaries and Rejoinder to "Do Switching Costs Make Markets Less Competitive?"

Vol. XLVI (August 2009), 446–452 446