It is impossible to generate a perfect demand forecast. What makes it impossible is noise—seemingly random or arbitrary fluctuations in demand. Noise is not forecastable. Many times, when planners manually adjust the forecast, they are trying to predict the noise that the forecast could not.
The limitation of traditional forecasting and demand planning systems is that they are deterministic; their internal processes view all data as exact. They take exact values as input, and they output exact values. The forecasting calculation is unaware of the uncertain nature of the demand.
That’s why, with a traditional forecast, it’s impossible to cleanly separate signal from noise. Any deviation in demand, however normal, is considered as error, since the forecast is an exact number. Any noise also shows up as variability and is accounted for in exactly the same way as the variability in the signal.
Demand modeling works differently. It separates the signal and the noise. Signal is data that has predictive value. Noise does not. So when you model demand, you don’t try to guesstimate the noise. It’s futile to attempt to predict it, so why waste the time, effort, and cost? Instead, demand modeling improves the forecast by getting progressively better at isolating the signal from the noise.
In demand modeling, everything is “stochastic.” Derived from the Greek word stokhastikos—to aim at the mark— stochastic modeling systems train their sights on a more accurate forecast by modeling probabilities and factoring in random behavior. This means a stochastic outcome can have any value within a range, and each value has a certain probability of occurring. So for example, rather than saying that the predicted outcome of tossing two die is 7, the stochastic profile of the predicted outcome would be a range of outcomes from 2 to 12 with a probability of 1/36 for 2, 1/18 for 3 … up to 1/36 for 12.
Demand modeling considers the range of values and their probabilities—utilizing the fact that demand and supply are uncertain. The signal is not an exact number but a range of values, each with a probability of occurring—just like overall demand in the real world. There is variability, but the variability is part of the signal. The difference between signal and noise is the portion of demand that is predictable and the portion that is not. Using our die toss example, rolling a total of 2 is not considered a forecast error, but a normal—albiet unlikely — outcome of the die toss.
So traditional forecasting ignores the inherent stochastic nature of demand. Demand modeling embraces it.
In modeling demand, the signal is determined by “decomposing” the data into a signal and a noise portion. It makes the granularity of this baseline demand as detailed as possible. The more detail, the more signal is preserved—and the clearer the signal can be identified from within the noise. The most commonly used granularity is individual sales order-line, daily by item and by ship-to location.
From this detail, all kinds of patterns can be identified. For example, each ship-to location may show clear ordering patterns favoring certain days of the week, and may exclude other days completely, like Saturdays, Sundays, and holidays. Similarly, there may be obvious patterns for weeks within the month, driven by sales targets in fiscal calendars. This detail allows the signal to be automatically detected.
Additional information—seasonality, promotions, market intelligence—further fine-tunes the separation of signal from noise for a “quieter,” more accurate forecast (See the diagram at the top of the page). As additional information is provided, every last bit of signal is isolated from the noise.
If you are interested in learning more about Demand Modeling, read the first part of this series – Don’t Forecast Demand, Model Your Demand
Next week, we’ll move from Demand Forecasting and Analytics to Supply Chain Planning, with the first of two blogs on a fascinating trend in planning technology.