WINNER: 04.01 “Sales Territory Design: 30 Years of Modeling and Implementation”
by Andris Zoltners and Prabhakant Sinha

ZS Associates, a large marketing science consulting firm, traces the evolution of models and processes over a 30-year period, during which they developed and implemented their sales territory alignment approaches in over 1,500 projects for over 500 companies in 39 countries and designed an estimated 500,000 sales territories. Those implementations have lead to revenue increases of 2% to 7% for these companies or over $5 Billion in total. The increase in effective selling time with their approach has a capacity equivalent to 12,500 added salespeople. Technology has enabled the models to get closer to sales managers, and they describe an effective implementation processes that enhances the model-based answer and generates sales manager buy-in at the same time. They describe a process that first creates a model-based answer, then integrates field manager input in a structured way by having the manager work one-on-one with an alignment expert and the model. This process led to a 100% implementation rate for the models.

04.02 “Attribute Drivers: A Factor Analytic Choice Map Approach for Modeling Choices Among SKUs”
by Ashish Sinha, J. Jeffrey Inman, Debbie Samuels and Yantao Wang

IRI developed a product called Attribute Drivers that is used by a number of its key clients to understand consumer’s choices among SKUs. The application of this approach at Campbell’s Soup helped Campbell’s grow revenues at twice the category growth rate during a climate of high product proliferation, a slow economy and a five-year decline in sales. The model helped the company make decisions pertaining to re-staging one of the brands in the portfolio, and fuels a decision support system that enables the company to identify the optimal mix of products at the national level as well as at the account level (e.g., Kroger). The model has been used in the shaving category to understand the price gap between the client’s brand and the premium brand in the category, thereby helping the client make more effective pricing decisions and in the salty snack category in to support the addition and deletion of SKUs. The model has been successfully applied to 22 client situations across 12 companies.

04.03 “CHAN4CAST: A Multi-Channel Multi-Region Forecasting Model and Decision Support System for Consumer Package Goods”
by Suresh Divakar, Brian Ratchford , and Venkatesh Shankar

Pepsico developed a model and decision support system called CHAN4CAST to forecast sales for consumer packaged goods. The model decomposes sales into several channels, including grocery, drug, convenience and gas, fountain and the like, decomposing sales forecasts into different channels. The model also incorporates holidays, temperature, trading day effects and new product introductions. The model’s mean percentage forecast error for the grocery channel in 2003 was -0.4%. The associated DSS allows product managers both to plan for forecast sales volumes as well as to simulate the effect of different firm and competitors’ actions on those sales. The tool includes a scorecard by account, channel and region that allows Pepsico to continually track its sales against forecast. The company estimates benefits as well over 1000% return on the model investment.

04.04 “Modeling the Effects of Direct Television Advertising”
by Rajesh Chandy, Deborah MacInnis, Gerard J. Tellis, and Pattana Thaivanich

Futuredontics, a dentist referral service (1-800-DENTIST), advertises this service in over 60 major markets in the U.S., with a multi-million dollar advertising budget that includes over 3500 TV ad exposures per month. The firm was concerned about more efficient spending, and applied a model that determines which particular ads are effective, when (at what times), where (in which medium) and for how long, an analysis at the highly disaggregate hourly level. The firm used the results about baseline sales and advertising carryover to assess call center staffing and to schedule call center operators in a manner that minimized wait times. It also adopted an advertising schedule that focused on heavier advertising in the early part of the week, a Sunday to Tuesday schedule, or a Monday to Wednesday schedule, and completely dropped advertising on Thursdays, Fridays, and Saturdays, providing a savings of 10 to 15% of media expenditures or approximating $1 million annually.