Forecast bias

Bias says which way a forecast was off, compared with what actually sold.

About 5–10 minutes · no sign-up needed

The idea

Bias says which way a forecast was off, compared with what actually sold:

( Forecast − Actual ) ÷ Actual

BiasWhich way the forecast was off, as a share of what sold.

Positive: too highAudio planned 1,000 and sold 800: (1,000 − 800) ÷ 800 = +0.25, so +25%. Too much stock, left on the shelves.

Negative: too lowPower banks planned 300 and sold 400: (300 − 400) ÷ 400 = −0.25, so −25%. Too little stock, and missed sales.

Aim for a bias near 0%: small misses either way cancel out. A bias with the same sign month after month means the forecast needs adjusting.

Try each one in your head first, then open the answer.

1. In D2, work out Audio's bias, as a decimal (no × 100).

=(B2-C2)/C2

2. What was Screen guards' bias?

(450 − 500) ÷ 500 = −0.1, so −10%

3. Tap the category with the most negative bias: it sold the most above its forecast.

Power banks sold 400 against a forecast of 300: a −25% bias.

4. Cases has a +20% bias. What does that mean for the stockroom?

There's more Cases stock than customers are buying

5. Audio's forecast has been 25% too high for three months. What should the planner do?

Lower the Audio forecast

Learn it by doing. This lesson is a short hands-on level on Bampaa: see it work, then build and write it yourself, with instant feedback.

About 5–10 minutes · no sign-up needed