Why forecasting is important (even if not highly accurate)


"Why forecasting is important" gets searched over 100 times monthly on Google. Search results include plenty of rah-rah articles touting the obvious benefits of an "accurate forecast," but are of little help in the real life business world where high levels of forecast accuracy are usually not achieved. This is a troubling disconnect.

When can we forecast accurately?

photo of sunrise
Why forecasting is important? So we know when to get up in the morning.

We can forecast the exact time of sunrise tomorrow, and indefinitely into the future.

Why is this? Because we have good observational data (the relative positions and velocities of the sun and planets in our solar system). And we seem to have a pretty good understanding of the laws of physics that guide the behavior being forecast.

[For some interesting background, see How is the time of sunrise calculated?]

Climate and weather are guided by the same laws of physics (and also chemistry) that we seem to have a pretty good understanding of. Yet we can't expect to forecast long term climate (or even near term weather) as accurately as sunrise for a number of reasons:

  • photo of lightning
    Why forecasting is important? So we avoid lightning.

    The climate is a much more complex system. It is not nearly so easy to model as a dozen or so heavenly bodies hurtling through space.

  • Our observational data is limited to a finite number of monitors and weather stations. So there are gaps in our knowledge of the complete state of the system at any given time. (We cannot monitor every single point of land, sea, and atmosphere.)

In addition, the assumptions upon which a long term forecast is based can change over time. There may be a change in decisions or actions in response to the original forecast. [Snurre Jensen examines this phenomenon in "When poor forecast accuracy is a good thing."] For example:

  • A business increases advertising when the demand forecast falls short of plan.
  • Politicians take action to reduce CO2 levels based on a forecast of warming.

[Despite the implausibility of the second example, I want to commend Nate Silver's The Signal and the Noise for its extremely informative chapter on climate forecasting (and on forecasting in general).]

Why forecasting is important

Highly accurate forecasting, while always desirable, is rarely necessary. In fact, if your organizational processes NEED highly accurate forecasts to function properly, I suspect they don't function very well.

As long as forecasting can get you "in the ballpark," and thereby improve your decision making, it has demonstrated its value. Remember the objective:

To generate forecasts as accurate and unbiased as can reasonably be expected -- and to do this as efficiently as possible.

Why forecasting is important is that it at least gives us a chance for a better future.


About Author

Mike Gilliland

Product Marketing Manager

Michael Gilliland is a longtime business forecasting practitioner and formerly a Product Marketing Manager for SAS Forecasting. He is on the Board of Directors of the International Institute of Forecasters, and is Associate Editor of their practitioner journal Foresight: The International Journal of Applied Forecasting. Mike is author of The Business Forecasting Deal (Wiley, 2010) and former editor of the free e-book Forecasting with SAS: Special Collection (SAS Press, 2020). He is principal editor of Business Forecasting: Practical Problems and Solutions (Wiley, 2015) and Business Forecasting: The Emerging Role of Artificial Intelligence and Machine Learning (Wiley, 2021). In 2017 Mike received the Institute of Business Forecasting's Lifetime Achievement Award. In 2021 his paper "FVA: A Reality Check on Forecasting Practices" was inducted into the Foresight Hall of Fame. Mike initiated The Business Forecasting Deal blog in 2009 to help expose the seamy underbelly of forecasting practice, and to provide practical solutions to its most vexing problems.

Back to Top