Final Predictive Analytics World presentation for me – Walmart Financial Services and Mu Sigma talking about marketing mix modeling. Walmart Financial Services focuses on the unbanked or under-banked. Specific services like money transfers, check cashing can be quite high volume in some locations and some 1,000 locations have branded MoneyCenters. Mu Sigma is an Indian pure-play analytics company focused on helping organizations to institutionalize analytics through dedicated analytic centers. Walmart uses Mu Sigma for a lot of their analytic support.
Marketing in WFS had common problems – are investments being made wisely, are results worthwhile, what’s the appropriate marketing budget. They lacked standard ways to measure results and lots of decisions were not made analytically. Finally the nature of the WFS customer base made tracking difficult. They needed a repeatable, believable process that standardized the measurement process, establish a communication platform and predict effectiveness.
WFS uses transaction life analysis around run rate and growth, price / mix analysis, financial returns and qualitative analysis of the creative. Marketing Mix modeling, optimization, let’s them see the effect of individual campaigns (there’s a lot of Walmart stuff going on in the market), account for seasonality and manage at the store level. The idea is to make sure the marketing investment is optimized, targeted and repeatable.
Marketing mix optimization uses weekly sales, store traits and demographics, event information and macro-economic data to see how effective specific events were and what was the contribution to the overall effect. What was the value or contribution of each element, did they cannibalize each other, did they resonate in specific areas etc.
Walmart’s culture creates some challenges. It takes too long for results and Walmart believes in rapid execution. Walmart people like to see the numbers and these models are opaque. Finally there are lots of local activities, promotions etc that are hard to capture. This meant they had to support these models with other techniques that were less opaque, they had to focus on specific campaigns to get quick execution and they developed a scenario gaming tool to help get buy in.
Over time their plan is to build an integrated solution that brings in a business context, exposes the marketing mix modeling inputs, connects up a data mart and provides an analyst workbench to handle data collection, modeling and output.
Comments on this entry are closed.