Customer management activities at firms involve making consistent decisions over time, about: (a) which customers to select for targeting, (b) determining the level of resources to be allocated to the selected customers, and (c) selecting customers to be nurtured to increase future profitability. Measurement of customer profitability and a deep understanding of the link between firm actions and customer profitability are critical for ensuring the success of the above decisions. We present the case study of how IBM used customer lifetime value (CLV) as an indicator of customer profitability and allocated marketing resources based on CLV. CLV was used as a criterion for determining the level of marketing contacts through direct mail, telesales, e-mail, and catalogs for each customer. In a pilot study implemented for about 35,000 customers, this approach led to reallocation of resources for about 14% of the customers as compared to the allocation rules used previously (which were based on past spending history). The CLV-based resource reallocation led to an increase in revenue of about $20 million (a tenfold increase) without any changes in the level of marketing investment. Overall, the successful implementation of the CLV-based approach resulted in increased productivity from marketing investments. We also discuss the organizational and implementation challenges that surrounded the adoption of CLV in this firm.

This study addresses significant challenges that practitioners face when using customer lifetime value (CLV) for customer selection. First, the authors propose a Bayesian decision theory-based customer selection framework that accommodates the uncertainty inherent in predicting customer behavior. They develop a joint model of purchase timing and quantity that is amenable for selecting customers using CLV. Second, the authors compare performance of the proposed customer selection framework (1) with the current customer selection procedure in the collaborating firm and (2) with different customer-level cost allocation rules that are necessary for computing CLV. The study finds that given a budget constraint, customers selected by means of a Bayesian decision theory-based framework (i.e., using the maximized expected CLV of a customer and the corresponding optimal marketing costs as an estimate of future costs) provide the highest profits. The study provides guidelines for implementation and illustrates how the proposed customer selection framework can aid managers in enhancing marketing productivity and estimating return on marketing actions.

Each customer varies in his/her lifetime value to a firm. A firm would like to estimate the lifetime value of each customer and use this information in planning differential marketing initiatives targeted at each customer. Customer lifetime value computations require different approaches depending on the business application that a firm is looking at. The authors present two approaches of computing customer lifetime value and offer some best practice applications. The authors also address challenges that firms typically face in implementing the customer lifetime value approach to marketing.

The terms relationship marketing (RM) and loyalty have been extensively promoted in marketing literature. Advocates of RM and loyalty have argued that RM leads to loyalty and loyalty leads to profitability. However, currently available evidence questions these arguments. We propose a term relationship intention. Relationship intention is willingness of a customer to develop a relationship with a firm while buying a product or service attributed to a firm, brand, and a channel. We build a multi-item scale for measuring relationship intention. We propose a framework, wherein we argue that the relationship intention is influenced by the customers’ perceived firm equity, perceived brand equity, and perceived channel equity. We propose the consequences of relationship intention as being low cost to serve, price premium, word-of-mouth promotion, and company advertisement. We also argue that relationship intention moderates the association between lifetime duration and profitability. Finally, we discuss the managerial implications of relationship intention in terms of transaction and RM

In an unpredictable global marketplace, managers face the constant challenge of trying to determine where their company is headed next. They must respond quickly and effectively, using only a handful of levers to help build sales and marketing efficiency and market share. This is where decision models can play a key role. By providing headlights for predicting future short and longer term sales response activity, they can help managers make better decisions. By definition, decision models are used to predict the outcomes of marketing-mix decisions. At the most basic level, decision analysis models input sales response variables – such as market-size/opportunity, demographics, and/or firmographics, marketing communications, price, and promotional offers – into a database. Then, by using typical mathematical techniques, they predict how the market will respond to changes in the analyzed set of variables. The result can help measure the effectiveness of marketing efforts and provide decision support for actual decisions. Decision models are most useful when they’re backed with relevant, timely, and accurate data and variables. With a good mix of variables, decision models can deliver useful information to help managers reach decisions. Decision models can be used to answer several “if this-then-that” questions. Just as in descriptive models, they can find a regular pattern to predict how a market will react to changes in marketing-mix variables. With this information, the manager has a better chance of finding the correct solution than by depending on intuition or non-empirical data.

Prior research assessing the predictive validity of alternate market share models produced conflicting results and often found that econometric models performed worse than naïve extrapolations. However, contributors to IJF's recent issue on market share models suggested that such models are often misspecified, in part because they exclude promotional variables and are estimated on aggregate data. Thus, we used weekly scanner data to assess full, reduced, and naïve form for linear, multiplicative, and attraction specifications across different levels of parameterization. Consistent with specification-based arguments (1) econometric models were superior to naïve models, (2) GLS estimates of attraction models were superior when models were fully specified, (3) OLS estimates of linear models were superior when models omitted important variables, and (4) attraction models predicted best overall. Moreover, in general, unconstrained models yielded superior forecasts relative to constrained models because brand-specific parameters were heterogeneous for the product category tested.