Demand sensing

Demand Sensing is a next generation forecasting method that leverages new mathematical techniques and near real-time information to create an accurate forecast of demand, based on the current realities of the supply chain. The typical performance of demand sensing systems reduces near-term forecast error by 30% or more compared to traditional time-series forecasting techniques. The jump in forecast accuracy helps companies manage the effects of market volatility and gain the benefits of a demand-driven supply chain, including more efficient operations, increased service levels, and a range of financial benefits including higher revenue, better profit margins, less inventory, better perfect order performance and a shorter cash-to-cash cycle time. Gartner, Inc. insight on demand sensing can be found in its report, "Supply Chain Strategy for Manufacturing Leaders: The Handbook for Becoming Demand Driven." ^[1]

The principles of demand sensing apply across industries and to any large company in the supply chain, including manufacturers, retailers or suppliers. Well-known companies that have implemented demand sensing strategies and technologies include Procter & Gamble, Unilever, Kraft Foods, Kimberly-Clark and General Mills.

Traditionally, forecasting accuracy was based on time series techniques which create a forecast based on prior sales history and draws on several years of data to provide insights into predictable seasonal patterns. However, past sales are frequently a poor predictor of future sales. Demand sensing is fundamentally different in that it uses a much broader range of demand signals (including current data from the supply chain) and different mathematics to create a more accurate forecast that responds to real-world events such as market shifts, weather changes, natural disasters, consumer buying behavior etc.

Companies with large global supply chains tend to benefit most from demand sensing. As such, demand sensing systems must scale to process masses of data associated with hundreds of thousands of items and location combinations every day. The sheer volume, frequency and small processing window require automation and the application of mathematics in a structured way to ensure that results published daily to Supply Chain Planning systems to build, distribute and order products or components are accurate and consistent.

Market Forces Behind Demand Sensing

Demand sensing emerged from the need to improve demand forecast accuracy in supply chain planning, decrease inventory costs and increase profits. As part of a drive to increase flexibility and responsiveness from suppliers, retailers (and, in turn, manufacturers) have reduced product order times and lowered their inventories, shifting the inventory burden upstream to suppliers. In parallel, manufacturers, retailers and suppliers are all are under pressure from investors to free up working capital by reducing inventory levels. These events, along with changing consumer behavior and rising market volatility, have underscored the opportunity to sense and react in near real-time to changes in the supply chain and exposed the limitations of traditional forecasting techniques.

History and Limits of Traditional Forecasting

The cornerstone of traditional forecasting is based on the Fourier series time series mathematical analysis conceived by Joseph Fourier in 1822. Fourier statistical modeling uses a historical data series to create seasonal forecasts and set the course of forecasting for the next 125 years. In 1957, Holt-Winters took time series analysis to a new level with exponential smoothing. In the 1980s, low-cost computing paved the way for larger and more complex time-series models and Moore’s law continues to fuel the trend of increasingly sophisticated models in the pursuit of refining forecast accuracy.

There remains, however, a ceiling for time series forecast accuracy. A ceiling governed not by processing power and memory, but rather fundamental limitations imposed by information theory and the fact that historical data does not reflect current events or market conditions.

• Information theory dictates that increasing model sophistication to pursue a “perfect fit” reaches a point where further sophistication of time-series analysis actually decreases forecast accuracy. Industry figures show that despite highly-tuned models, forecast error remains a challenge. Even high-volume products with well-understood seasonality patterns established over decades continue to experience high near-term forecast error rates using sophisticated traditional time-series methods for demand planning.
• Furthermore, historical data series are by nature disconnected from current events that effect demand in unpredictable ways – a financial downturn or recovery, a spike in energy prices, an outbreak of swine flu, regional unrest or natural disasters. Even changing weather patterns such as cold snaps and heat waves alter consumer demand from historical patterns. It therefore comes to no surprise that time series models are ill-suited to volatile markets, especially during market downturns or upturns.
• Information theory dictates that increasing model sophistication to pursue a “perfect fit” reaches a point where further sophistication of time-series analysis actually decreases forecast accuracy. Industry figures show that despite highly-tuned models, forecast error remains a challenge. Even high-volume consumer packaged products with well-understood seasonality patterns established over decades continue to experience high near-term forecast error rates using sophisticated traditional time-series methods. A recent study encompassing $200 billion of trade from nine multinational CPG companies with 70,000 items and 300,000 item-location combinations found that the top quintile of highest volume products (1% of items representing 20% of total volume) had an average time-series forecast error of 43%, while the lowest quintile of slowest moving products( 85% of products representing 20% of the total volume) had an average forecast error of 65%.

Adding Current Data

Breaking this ceiling requires the inclusion of current demand signals from throughout the supply chain and new mathematics to sort through the masses of data and determine what is predictive. There is no shortage of near real-time data collected by manufacturers in their supply chain and it grows exponentially, once retailer data is included. According to a McKinsey & Company report, “Manufacturers can improve their demand forecasting and supply planning by the improved use of their own data. But as we’ve seen in other domains, far more value can be unlocked when companies are able to integrate data from other sources including data from retailers, such as promotion data (e.g., items, prices, sales), launch data (e.g., specific items to be listed/delisted, ramp-down plans), and inventory data (e.g., stock levels per warehouse, sales per store). By taking into account data from across the value chain (potentially through collaborative supply chain management and planning), manufacturers can smooth spiky order patterns. The benefits of doing so will ripple through the value chain, helping manufacturers to use cash more effectively and to deliver a higher level of service. Best-in-class manufacturers are also accelerating the frequency of planning cycles to synchronize them with production cycles. Indeed, some manufacturers are using near-real-time data to adjust production.” This last sentence refers to demand sensing solutions. For more information see McKinsey Global Institute's report, "Big Data: The Next Frontier for Innovation, Competition and Productivity." ^[2]

Lora Cecere, Partner, Altimeter Group, explains the process of using retailer data, also referred to as downstream data, to enhance demand sensing performance. “It is hard work. It is cross-functional. It is a new way of thinking. At the core, it challenges traditional paradigms. However, if you can cross these boundaries, companies find that the use of downstream data pays for itself in less than six weeks every six weeks, and companies that were good at the use of downstream data and sensing channel demand aligned and transformed their supply chains 5X faster than competition.” For more information see Lora Cecere's post on downstream data.^[3]

Why Better Forecasts

The pursuit of better forecasts is not an academic exercise. Better forecast translate directly into better business decisions. According to Lora Cecere, “what is a 6% improvement in forecast accuracy worth? Based on AMR Research correlations, a 6% forecast improvement could improve the perfect order by 10% and deliver a 10-15% reduction in inventory. The greatest impact is seen in slow moving items on the tail of the supply chain.” Cecere also comments “Procter and Gamble attributes their work with Terra Technology and the use of downstream data to a 2.5 billion dollar reduction in inventory.” For more information see Supply Chain Shaman.^[4]

Infusing demand sensing into the demand management process can affect many Key Performance Indicators (KPI) closely monitored by management:

• Financial KPI's

o Revenue and Profit Margins: sense and react to upswings in demand to capture additional revenue and increase profit margins by avoiding costly supply chain inefficiencies stemming from demand uncertainty.

o Cash-to-Cash Cycle Time: Free up cash flow and achieve higher return on invested capital by reducing inventory levels of products.

• Supply Chain KPI's

o Perfect Order: Improve customer service by producing the right product mix matched to actual demand.

o Production Efficiency: Stabilize production schedules and avoid emergency changeovers to meet surges in demand.

o Logistics: Reduce transportation costs by avoiding transshipments and expensive emergency shipments; and reduce warehouse costs with lower inventory levels.

References

1. ^ Jane Barrett, Michael Burkett, Hussain Mooraj, Gartner, July 15, 2010 “Supply Chain Strategy for Manufacturing Leaders: The Handbook for Becoming Demand Driven.”
2. ^ James Manyika, Michael Chui, Brad Brown, Jacques Bughin, Richard Dobbs, Charles Roxburgh, Angela Hung Byers, McKinsey Global Institute, May 2011, “Big Data: The Next Frontier for Innovation, Competition and Productivity.”
3. ^ Lora Cecere, Supply Chain Shaman, December 20, 2010, “Three Things I Have Learned about Using Downstream Data.”
4. ^ Lora Cecere, Supply Chain Shaman, February 28, 2011, “Trading Places.”

External links

• Consumer Goods Technology Unilever Gets a Better Sense of Demand [1]
• Business Logistics Procter & Gamble implements Terra’s short-term Demand Sensing [2]