Skip to content

Stockertim Dictionary · Strategy and management · Technology

Forecast error

Also called forecasting error, forecast bias

In short

Forecast error is the difference between actual demand and the forecast for the same period, tracked over time to judge and improve a forecast.

  • Intermediate
  • Ratio or metric
  • Checked

In detail

No forecast is exact, so the useful question is how wrong it is and in what way. Forecast error for a period is usually calculated as actual minus forecast: a positive error means demand was higher than forecast, a negative one that it was lower. Looking at errors across many periods reveals two different problems.

The first is bias, a tendency to be wrong in the same direction. If errors are mostly positive, the forecast is consistently too low, which leads to stockouts; if mostly negative, it is too high, which builds excess stock. Bias is measured by the average error or a running sum, and a tracking signal compares that sum with the typical size of errors to flag when a forecast needs attention. The second problem is accuracy, the typical size of errors regardless of direction, measured by the mean absolute deviation, mean squared error or mean absolute percentage error.

Tracking error matters because it shapes safety stock and trust. Planners size buffers according to how large errors usually are, and teams who see errors analysed openly can find causes, such as promotions not shared with planners, rather than adjusting numbers by gut feel.

Formula

Forecast error = actual − forecast

actual
demand that occurred in the period
forecast
demand that was forecast for the period

Worked example

Over four weeks a shop, Tidewater, forecast 100 units a week and sold 110, 95, 120 and 105.

  1. Errors: 110 − 100 = 10, 95 − 100 = −5, 120 − 100 = 20, 105 − 100 = 5
  2. Sum of errors: 10 − 5 + 20 + 5 = 30

The errors add to 30 over four weeks, a sign the forecast is biased low.

In practice

Demand planners review forecast error by product each month, and sales and operations planning meetings discuss large or persistent errors and their causes.

Watch out

  • Positive and negative errors cancel in an average; check absolute errors too.
  • Some teams define error as forecast minus actual, so check the sign convention.

Learn it properly

Official sources

Facts last checked on 3 November 2026.

Education, not advice: the Stockertim Dictionary explains what terms mean. It never recommends buying or selling anything.

English