Forecast error (WAPE)
Σ |actual − forecast| ÷ Σ actual over the slice
- Formula
Σ |actual − forecast| ÷ Σ actual over the slice- Unit
- %
- Aggregation rule
- Ratio of sums
- Source system
- Plan and budget model; POS: receipts
- Owning role
- Analyst (BI)
- Frequency
- Monthly
Passport
- Grain
- SKU × week → slice (category, channel)
- Numerator
- Sum of absolute errors over the slice Σ|actual − forecast|
- Denominator
- Sum of actuals Σ actual over the slice
- At zero or no data
- Sum of actuals is 0: “—”; individual zero-actual periods are not dropped.
- Limits
- Add over the slice first, then divide: SKU errors are not averaged. Zero actuals in single rows are fine, unlike MAPE. One forecast horizon.
- Check example
- Sum of absolute errors, units: 40; Sum of actuals, units: 260.
a/b*100. Result: 15.4% - Related metrics
Version 1.0 · valid from 2026-11-16 · checked 2026-11-16
Related pages
- Term: Forecast error (WAPE) and bias
- Calculation: Sales forecast: method, horizon, error
Definition
WAPE is the total deviation of forecast from actual; bias shows whether the method overstates or understates.
Computed on past data, so it is an estimate, not a guarantee. For seasonal apparel the error is higher than for basics: check it on your own past seasons.