For Procter & Gamble, supply chain management is a core competency that requires continuous reinvestment to improve performance and competitive advantage. The company recently undertook an initiative to boost its short-term forecasting accuracy as a way to lower safety stocks. Dick Clark, associate director for demand planning for Procter & Gamble, selected Terra Technology's Demand Sensing solution as a bolt-on addition to its SAP system. Terra's so-called "black box" solution takes existing forecast information from the demand plan, combines it with other real-time data like daily shipments and orders, and applies complex pattern recognition algorithms and other formulas to create forecasts on a daily basis for every product at the line item level.

"Terra essentially reruns the forecast and replaces the first 42 days of the SAP forecast," says Mark Kremblewski, global business expert on demand planning for Procter & Gamble.

The program automatically updates these forecasts daily based on real-time data on orders and shipments as they continually flow into the system. Once the demand plan is created and sent, virtually no human interaction is required.

Since Terra is predicting shipments to customers, capacity constraints are taken into account afterwards through distribution resource planning (DRP) and production scheduling. Further, it takes a weekly granular forecast and replaces it with a daily granular forecast.

"It is more than a different 'split by day'," says Kremblewski. "It will modify the weekly quantity if that is more accurate."

The SAP forecast is still important as it provides one of the inputs to the black box, but Kremblewski points out that forecast error typically accounts for about 90 percent of safety stock.

"If you plan your supply chain using the forecast to set inventory targets, over a zero-to-28-day horizon, I'd say you'll at a minimum reduce inventory by 10 percent. Looking at actual pilot results in some supply chains, we've actually seen examples much higher than that," says Kremblewski. 

Procter & Gamble is live on the software in several business segments in Western Europe and North America and is rolling the software out globally over the next few years. Safety stock has decreased by more than 10 percent in the businesses where the software is live. Out-of-stocks as a result of incorrect safeties did not increase.

Procter & Gamble anticipates that the greatest benefit from adopting this type of solution may come over the long term, as P&G shifts its demand planners away from the inevitable firefighting and scrambling inherent in focusing on short-term forecasts.

"Our demand planners have more than enough things to do without focusing on the next one, two or three days, or the next week," Kremblewski says. "The 'black box' takes care of all that, which allows our demand planners to focus on the longer term, on the trends, on the business intelligence regarding the marketplace, what our customers are doing, etc. And that's where their real value is added, not watching orders or watching short-term trends. If the box can do it, let the box do it."