Please accept all cookies to ensure proper website functionality. Set my cookie preferences

The famous department store mogul, John Wanamaker, is reported to have said, "I know that half my advertising works, I just don't know which half."

This statement typifies the "feel-good marketing" paradigm. But in today's scarcity economy with layoffs and radical cost cutting, companies must acquire the tools and processes to move beyond it—to a new, "accountability marketing" paradigm.

Marketing response modeling (MRM) is a tool that applies science to a company's sales data and mathematically determines the precise contributions of each marketing element; it enables a company to truly understand the returns on investment from its marketing spending. In other words, these tools are specifically designed to tell you which half of your ad budget is working, and which is not.

This article will explain what the adoption of MRM entails and how it can help large or small companies to move toward this new paradigm of accountability marketing. Above all, this article will try to articulate a process whereby firms can harvest the benefits of these tools and plug them into their formal business planning processes.

We stated that MRM is a technology that applies science to marketing data. In effect, it begins with the collection of end-user sales data over time and links to that various marketing initiatives such as TV advertising, promotions, direct mailings, call center leads, pricing and external non-marketing factors that have an impact on the business, such as the economy or weather.

All of that is designed to work together for the analyst, who will build cause-and-effect statistical and predictive models of a firm or product's end-user sales.

So, the process of doing an MRM project first starts with data collection, all of which needs to be customized around each firm's unique business model. Not all firms use the same marketing tactics; some firms' end-users are businesses, whereas others are consumers. Design, and due diligence in collecting the information up front, is step-one in completing a successful MRM engagement.

Once that is done, competent modelers are plugged in to construct valid and predictive mathematical models.

And once that is completed, the analysis takes three basic steps:

  1. Diagnostics. Here, the analyst looks at recent and past marketing efforts to link each marketing activity to the sales output and come up with an assessment of what's working or not working. This usually entails linking marketing expenditures to the marketing-driven sales of each marketing element and coming up with "efficiency ratios," such as "expenditures per incremental sale." Further diagnostics can be done by linking the sales contributions of each marketing element to financial margins and cost data to arrive at a complete return-on-investment evaluation of each marketing program.

  2. Optimization. Once the analyst has derived each marketing element's sales-driven values, the next step is to link model "elasticities" with an optimization engine and financial data. Here—whether looking across products, geographies or types of marketing activities within a single product—the optimization is designed to maximize sales or profitability, subject to some marketing spending constraint. Through this exercise, evidence will also become clear about which marketing elements are more or less efficient, and the optimization will drive spending away from the inefficient to the more efficient, resulting in some net gain or benefit to the firm.

  3. Strategy simulation. This entails plugging in marketing and business plans into the model. From explicit go-to-marketing strategies, the analyst should be able to build a simulator that not only estimates the impact of a given strategy but also quantifies the contributions from individual marketing elements. For example, one company's strategy might entail raising prices 2%, increasing ad spending 20% and reducing promotion spending 10%. Using the MRM models, simulations can be designed to estimate the impact of numerous scenarios.

Already, companies have adopted this tool, especially in consumer goods industries. A recent Mercer Management survey found that companies that have adopted MRM improved their marketing effectiveness on average 20-30%. Clearly, the savings and upside growth potential in applying these tools are substantial and could run into the millions.

For most companies, finding waste in a marketing plan or program is not difficult. In my experience, somewhere between 30% and 50% of marketing programs are either non-productive or grossly inefficient money losers.

Traditionally, marketing has been viewed as a highly intuitive discipline. That tradition says marketers are creative types who follow their instinct when it comes to marketing planning. Some of the decisions are supported by marketing research, for sure, but few marketers have any idea how spending on their marketing mix will produce specific results.

In today's scarcity economy, marketers can no longer afford to follow that paradigm. Market response modeling provides a compelling tool to help move marketing into a new era of accountability.

Continue reading "Which Half of Your Budget is Working?" ... Read the full article

Subscribe today...it's free!

MarketingProfs provides thousands of marketing resources, entirely free!

Simply subscribe to our newsletter and get instant access to how-to articles, guides, webinars and more for nada, nothing, zip, zilch, on the house...delivered right to your inbox! MarketingProfs is the largest marketing community in the world, and we are here to help you be a better marketer.

Already a member? Sign in now.


ABOUT THE AUTHOR

Michael Wolfe is president of Bottom-Line Analytics (www.bottomlineanalytics.com), a marketing research and consulting company specializing in online survey research, marketing-mix modeling, new-product forecasting and advanced marketing analytics. He is also an adjunct faculty member at the marketing response modeling (MRM) program of Terry College of Business at the University of Georgia.