Forecasting is the one quantitative technique that pays for itself in a mid-market company, and it is the one most often abandoned after a pilot. The abandonment is rarely about accuracy. It is about the forecast not being connected to a decision anyone actually makes.
A forecast that nobody acts on is a report. Reports get cancelled in the second budget round.
Why does forecasting help smaller companies more?
Because smaller companies have less slack to absorb being wrong. A large distributor with regional warehouses can move stock sideways when a forecast misses. A forty-person company with one warehouse cannot — it either holds cash in inventory it does not need, or it disappoints a customer. The cost of error is concentrated, which means the return on reducing error is concentrated too.
This is also why the sophisticated model is rarely the right first move. Most of the available gain sits in the gap between "no forecast" and "a competent simple forecast", not between a competent simple one and a very good one.
What you need before a model is worth building
Three things, in order, and none of them are algorithms.
A clean history of what happened, separated from what you did about it. Sales history is not demand history. If you were out of stock for three weeks, your sales record says demand was zero and your model will learn that. Stockouts, promotions and price changes have to be recorded distinctly, or the model is being taught your past mistakes as if they were customer behaviour.
A decision with a deadline. "How much do we order, and by when" is a decision. "What will next quarter look like" is a conversation. The forecast horizon must match the lead time of the decision — forecasting six months out when your supplier lead time is three weeks optimises the wrong number.
An agreed measure of wrong. Being 10% over and 10% under are not equally expensive, and most businesses know which one hurts. If you have not written that down, every forecast review becomes an argument about whether the model is good.
Which method, and when
| Method | Works when | Needs | Typical first result |
|---|---|---|---|
| Naive / last period | Demand is stable, lead times short | Nothing | The baseline everything else must beat |
| Moving average | Noise dominates, no strong trend | 6–12 periods of history | Beats intuition, costs nothing |
| Exponential smoothing | Clear trend and seasonality | 2–3 seasons of history | Where most SMEs should stop |
| Regression on drivers | Demand tracks a known external factor | The driver data, historically | Useful when drivers are real |
| Machine learning | Many SKUs, long history, real seasonality | Years of clean data, ongoing ownership | Rarely first, sometimes right |
The last row is the one companies ask about first. It is legitimate — it is also the only row that creates a permanent maintenance obligation, and it is the row most likely to be abandoned when the person who built it leaves. For a discussion of when that maintenance obligation is worth taking on, see AI adoption in Swiss companies: getting past the pilot.
Public statistical series can be genuine drivers rather than decoration. Swiss consumption, construction and trade indicators are published by the Federal Statistical Office, and for some categories one such series explains more variance than a year of model tuning.
How do you know the forecast is working?
Not by the accuracy metric. By whether the decision changed and whether the outcome improved.
The practical test is to run the forecast in parallel with whatever the business does today — usually an experienced person's judgement — for one full cycle, without letting it drive orders. At the end, compare both against what actually happened, and compare the cost of each error rather than the size of it. Judgement often wins on the fast-moving lines and loses badly on the long tail, which tells you exactly where to deploy the model and where to leave people alone.
This parallel run is also what makes adoption possible. A forecast imposed on a planner who was not consulted gets overridden quietly, and an overridden forecast produces no benefit while still costing maintenance.
Where this sits in a wider programme
Forecasting touches inventory, purchasing and finance at once, which makes it a useful first quantitative project and a poor first system project. If the underlying stock records are unreliable, fix those first — a forecast built on inventory data that does not match the shelf will be blamed for a problem it did not cause. Our quantitative strategies practice does a one-week data assessment before any modelling for exactly this reason, and it regularly ends with a recommendation to postpone the model.
For retail and consumer goods businesses specifically, the highest-value first cut is usually not all SKUs at once. It is the twenty lines that tie up the most cash, forecast properly, reviewed weekly by a named person. That is a fortnight of work and it is measurable by the following quarter.
Related reading
- Measuring ROI on digital transformation
- ERP for small companies: when it is time to move
- Quantitative strategies consulting
Working on this right now?
Tell us where you are in two questions. A consulting partner reviews every enquiry within 2 business days.