Economists have successfully predicted 9 of the last 5 recessions. (Jan Symankiewicz)
On small numbers, the error in deriving the forecast is almost as great as the error in believing it.
We've looked at forecast accuracy in isolation.
When we look at the costs of altering the plan after a change in forecast, we get a very different picture.
Where the cost of getting some changes right is outweighed by the costs of getting others wrong, don't re-forecast.
We often get better result with forecasting switched off.
Only forecast small numbers if you have no other method.
We should leak this (top secret) forecast to the competition - it's already done too much damage in house.
The rate of use for this product (disposable operating theatre supplies) is absolutely flat. If the demand is lumpy, it's something we are doing to ourselves (and it was!).
There's widespread belief that forecasting effort equals success 'because it should'. Mark Twain warns…
"What gets us into trouble is not what we don't know. It's what we know for sure that just ain't so."
Also George Bernard Shaw "…in the absence of good grounds for belief, [Man] will be satisfied with bad ones."