Forecasting & Intelligence

Simple demand forecasting for small retailers

A practical, low-effort approach to demand forecasting that doesn't require a data science background.

You don't need a data science team to forecast demand — a moving average of recent sales, adjusted for known seasonality and upcoming promotions, gets most small retailers most of the way there. The goal is a reasonable estimate, not a precise prediction.

Demand forecasting sounds like something only large retailers with data teams do. For most day-to-day reordering decisions, a much simpler approach gets you most of the value.

Start with a moving average

Take your sales for an item over the last several weeks and average them — this is your baseline expected demand for the next similar period. It's not sophisticated, but it's a real improvement over ordering based on memory or gut feel, and it automatically adjusts as recent sales trends shift.

Layer in known seasonality

If an item reliably sells more in a particular month or around a particular event, a flat moving average will underestimate demand right before it and overestimate right after. Adjust your baseline up or down around known seasonal patterns rather than treating every week the same.

Account for planned promotions

A moving average is built from normal sales — it won't predict a spike from a promotion you're about to run. If you know a discount or marketing push is coming, bump your forecast for that period manually rather than relying on the historical average alone.

What this is (and isn't) good for

This approach is good for routine reordering decisions on items with reasonably steady demand. It's not going to predict a genuinely unpredictable spike (see XYZ analysis for identifying which items fall into that category) — for those, a larger safety buffer is a more realistic tool than a more sophisticated forecast.

Where it fits into reordering

Forecasted demand feeds directly into your reorder point calculation (see our reorder points guide) — the more accurate your demand estimate, the tighter you can set your reorder point without risking a stockout.

StashBill's inventory intelligence builds this moving-average forecast automatically from your sales history.

Frequently asked

How far back should my moving average look?

4–8 weeks is a reasonable default for most retail items — long enough to smooth out noise, short enough to reflect recent trends.

Do I need historical data to start forecasting?

Yes, at least a few weeks of sales history — forecasting a brand-new item with no sales history relies more on comparison to similar items than on its own data.

Try it in the app that does this automatically

StashBill applies rules like these on every scan and every invoice, so you don't have to remember them.

Download Free

Get started free — no card required

Download StashBill and scan your first item in under a minute.

Simple demand forecasting for small retailers