Demand modeling is different from demand forecasting. Simply put, it doesn’t forecast demand, it models demand.
Forecasting typically starts with a time series of data—usually presented as a bar chart displaying demand by month or by week. It makes a projection of what will occur in future months based on what’s happened in aggregate over the last months or years.
For example, say you are a consumer goods company that makes orange juice products. If you want a national forecast three months out—based on the last couple of years, and factoring in trends and seasonality—you can probably forecast within a close approximation.
Model demand from the bottom up
The problem is that most supply chain decisions are not made at that level. The real question is, how many cartons of low-pulp, 16 ounce, SKU12345 orange juice are you going to need to ship from the Newark, NJ warehouse? Even if aggregate forecasts are only off by a few percentage points—the error can easily translate to a 40-50% error for a specific week, distribution center, and SKU combination.
This is because “splitting” algorithms take apart the total, apportioning 8% here, 12% there, but this doesn’t match real activity at the SKU level. When you aggregate you reduce the noise–the data gets smoother and forecasting is easier. But when you aggregate you also lose signal–signal that can never be retrieved again at the aggregate level. You trade away accuracy for ease. Read more in our blog: Probabilistic Planning and Forecasting Demystified
Demand modeling works in the opposite direction; from the bottom-up, as opposed to top-down. It breaks the demand components into a series of internal and external factors, the demand stream, and looks at how each impacts demand to predict future demand. It looks at the specific factors driving demand at a granular and daily level for individual SKU-Locations. It uses machine learning automation to leverage external demand-shaping factors such as new product introductions, promotions planning, end-of-aisle displays, and price reductions, that have an impact at the most detailed level and incorporates them into the forecast.
Build a probabilistic demand forecast
Demand modeling also processes the data differently and generates a different kind of output. Forecasting looks for a best fit from all available algorithms, generating a single value output. Demand modeling creates an adaptive demand distribution that best fits the demand profile. Probabilistic forecasting then produces a range of possible outcomes with probabilities assigned to all values within the range. It goes beyond the “demand forecast number” to the probability of demand in any given time period.
Modeling demand even helps with fast-moving goods, where demand appears consistent. When you model these items at the granular level, the demand may look more intermittent, irregular, and volatile. Forecasting algorithms call this unforecastable—they either can’t do it or can’t add enough value. Demand modeling breaks down this demand into its constituent parts, to understand its rationale and make a complete forecast across all your items.
Model demand for measurable business improvements
As for benefits, modeling demand can greatly improve the forecast accuracy—measurably in the aggregate and very significantly at the detailed level. It also reduces the manual intervention needed to get everything to work. When ToolsGroup replaces traditional forecasting with advanced demand modeling and forecasting, the planner workload is often cut in half as the computer handles more of the statistical workload and frees up the planner to focus more on the exception handling. For example, Melitta improved their management of promotions and increased their statistical forecast accuracy by 3.2% in the first six months.
Step Up to a Complete View of Demand
Figure – Step Up to a Complete View of Demand
The image above illustrates how ToolsGroup’s demand modeling approach allows you to layer demand insight to produce an optimal demand plan. We start with a baseline probabilistic forecast, augmented by our machine learning engine to incorporate seasonality and demand sensing data. Then we layer on media and promotions, new product introductions, special actions and events, and market intelligence. The demand model layers add increasing insight for an optimized demand plan.