When one billion units roll off your production line every day worldwide, accurate demand planning and forecasting are critical.

A global food supplier that also provides direct delivery to stores had outgrown their current demand forecasting software. Their system had become difficult to use, had a limited range of forecasting models and had difficulty forecasting demand when variables like promotions were added. The company at times had too much stock on hand, yet experienced stock outages during promotions.

Planning and forecasting in the food and beverage industry are highly complex, especially on a global scale. Seasonal swings in demand, availability of agricultural products for raw ingredients, retail trends, and the perishable nature of many products make it challenging to plan production and organize logistics. When you add promotional strategies and pricing, food and beverage forecasting becomes far more complicated – even marginal swings in accuracy can have a significant impact on profits.

In the food industry, products are processed in very large batches to keep unit prices low, ensure quality, and take advantage of raw ingredient availability. To have the right quantity of the right products in the right place at the right time, the company relies on predicting the orders their customers will place as precisely as possible. Strong alignment processes, close collaboration with customers, and proper forecasting methodology are critical to success.

The overarching goal for a new demand planning and forecasting solution was to allow the company to take proactive measures instead of simply reacting to changes in demand. Product categories, sales regions, and many departments provide input and all depend on accurate forecasting. Other business metrics, such as budgets, sales targets, promotions, and local demand are also factored. They wished to keep inventories within tight limits, proportionate with the size of their operations.

The wild card in forecasting is promotions

To ensure that the correct number of products make it to store shelves and into customers’ hands at the right times during a promotion, accurate forecasting is critical.

The company struggled with trying to factor in the impact of promotions. Repeatedly, their marketing promotions failed or underperformed when customers found store shelves empty during a promotion. The supply chain was guessing at how much product needed to be stocked for special promotions to drive sales volume and the sales team was guessing on what price to select to maximize profit. The existing solutions did a poor job of forecasting demand around promotions and much of the work was being done on spreadsheets.

Data was also scattered in many locations. Some was in regional offices which might be submitted once a week at the most. Forecast accuracy was decreasing for the division that handled delivery to pharmacy stores, and service issues and carrying costs were increasing. The company needed a robust, scalable solution with a user-friendly reporting system and one that didn’t require planners to spend most of their time administering data.

“Forecast accuracy improvement drives safety stock, inventory days on hand, storage costs and freight costs reduction. By gaining a few points of accuracy at the national level you can generate supply chain savings immediately.”  – Director of Supply Chain Integration.

SAS DDPO improved forecast accuracy by 4%

When the company implemented the SAS DDPO solution, forecasting improved immediately. The staff no longer needed two days to compute the data, including tens of thousands of time series calculations. Previously, when it took a long time to run data, information was released on a rigid schedule and was sometimes out of date. With SAS DDPO, it takes just a few minutes to update information, so planners can publish as they update.

“We saw our forecast accuracy improve immediately, we saw service take off in a positive way, and our inventories decreased,” said the Director of Supply Chain Integration. “We actually exceeded our original projections. Forecast accuracy improvement drives safety stock, inventory days on hand, storage costs and freight costs reduction. By gaining a few points of accuracy at the national level you can generate supply chain savings immediately.”

SAS DDPO shows a potential promotional lift for sales

The company’s SAS Demand Driven Planning and Optimization solution interacts with the sales team’s promotional planning system. The sales team enters the promotion details and can immediately see the projected lifts. The promotional plans are then used to drive the forecast used by the supply chain group to ensure that enough product is available to meet consumer demand. The sales teams also have the capability to measure the impact of in-store merchandising programs like end cap displays to determine the incremental unit volume impact, as well as revenue impact within designated market channels.

Using SAS DDPO, the demand planners can make calculations and let salespeople know, for instance, that there isn’t enough of the sale product in the pipeline near their territory to meet the estimated volume the promotion will generate. They can then work with sales to find a better promotion, help sales calculate the lift for a promotion, and determine whether a sales increase at that price will make the promotion profitable. Subjectivity is removed and replaced with data.

The results: SAS DDPO significantly improved the company’s forecast accuracy.

  • Exceeded 7% MAPE improvement
  • Improved forecast accuracy by 4%
  • Lowered inventory safety stock by more than 12%
  • Significantly reduced Excel spreadsheets
  • Supply chain is more efficient
  • Service levels improved
  • Measures the impact of promotions and price changes
  • Improved store-level forecasting during promotional cycles
  • Produces forecasts on a weekly basis to reduce overstocked shelves and lost revenue
  • Minimized inventory overstocks
  • Improved customer service levels
  • Reduced the cost of raw materials (commodities) by hedging daily swings in costs more accurately
  • Route planning is more efficient