After working across the organization to understand the critical drivers of current marketing success, Bain helped develop and test a set of offers in-market, by employing experimental design techniques. As opposed to the traditional champion-challenger approach, or A/B testing, the use of fractional factorial analysis allowed our media consultants to launch a subset of potential in-market offer combinations to test a number of different variables. Mathematical formulas then allowed us to model response rates for every possible combination of variables, 576 in all.
A second analytical tool was developed to project the financial impact of all offer combinations. This Net Present Value (NPV) model used both observed and modeled response and conversion rates as inputs, as well as key financial inputs based on CableCo's business-as-usual financials. The model allowed CableCo to not only determine what drives direct marketing conversion rates, but also to predict the actual financial impact of all potential offer combinations.
Experimental design improves testing performance through massive variance in the campaign: