This post is sponsored by AFS Technologies.
Consumer packaged goods manufacturers spend close to 20% of their revenue on trade promotion, and nearly 70% of events do not break even, according to a study conducted by EY, Sequoya Analytics and the Trade Promotion Optimization Institute.
In a webinar presented last week by AFS Technologies and SmartBrief, Joel Cartwright, director of product development for trade promotion management at retail for AFS and Mike Bruening, vice president of revenue management and optimization at Nielsen, discussed how predictive analytics can maximize lift and take the guesswork out of annual planning for CPG companies.
“[Using predictive analytics] I am going to be able to help you make that trade dollar go farther. I can help you increase topline growth and keep your trade spend flat. It’s about utilizing the data out there,” Cartwright said.
Leveraging data is the future
Nielsen and AFS have partnered to provide a low-cost, low-risk scenario planning capability. The Nielsen predictive model works within the AFS trade promotion management tool.
“We’re able to predict what would happen if you were to change a price or promote a certain way. [The model] allows users to see what the sell-through is going to be. We’re looking to build a correlation between what’s happening in the store and what the demand is,” Bruening said.
Cartwright emphasized that the tool puts predictive modeling within reach for companies both big and small. “Predictive capability will allow me to find the right point, the bare minimum I have to spend to deliver volume. Predictive analytics can work for brands of all sizes,” he said. “Leveraging data is the future.”
Spreadsheets don’t do enough
There’s a lot of data to consider when forming an annual plan, and many CPG companies rely on multiple spreadsheets to track it, with calculations completed by macros or by multiple formulas. AFS’s TPM tool and Nielsen’s predictive models combine in a single system, allowing account managers to consider the big picture.
“Nielsen’s predictive models put that capability in the hands of an account manager in the field, the person who’s creating that [trade promotion] plan, so they can say to the customer, ‘This is what the model is telling me’,” Cartwright said.
The models are fairly easy to implement, according to Bruening. “One of the key improvements we made on the modeling side is cost and time. We realized our processes had to be nimbler, faster, cheaper. We’re modeling at the store level, and we’ve made huge strides in delivering it faster and more affordably.”
With the AFS TPM tool, you can get the Nielsen models up and running within four to six weeks. The capability, the panelists said, is as simple as, but faster than, sending an email. AFS customer Sunny Delight found the forecasts to be accurate within about 2%, they said.
Moving from educated guess to informed prediction
Nielsen’s models, available within the AFS TPM tool, look at store-level data, predicting what would happen if a brand changed a price or promoted a certain way.
“The biggest obstacle [the account managers] will have to overcome is they’ll have to take a leap of faith and rely on what the predictive models are telling. But they don’t have to take that leap of faith all at once. They can take it customer by customer, product by product, and see where they want to go,” Cartwright said.
What’s more, he noted, the tool can make promotions more effective from the start.
“I can compare what it’s telling me from a consumption-data standpoint. But, instead of looking at it more in post-promotion, I’m more confident in the pre-promotion analysis,” he said. “It’s a lot easier to change an event before it happens than to get it changed later on downstream.”
For more information on using predictive analytics to maximize trade spend, and more insights from Cartwright and Bruening, listen to the recorded webcast.
If you enjoyed this article, join SmartBrief’s email list for more stories about the food and beverage industry. We offer 17 newsletters covering the industry from restaurants to food manufacturing.