Predictive Analytics: Microsoft® Excel

4. Forecasting a Time Series: Smoothing

In This Chapter:

Exponential Smoothing: The Basic Idea

Why “Exponential” Smoothing?

Using Excel’s Exponential Smoothing Tool

Choosing the Smoothing Constant

Handling Linear Baselines with Trend

Holt’s Linear Exponential Smoothing

In Chapter 3, “Forecasting with Moving Averages,” you saw how the number of values that are included in a moving average controls the relative amount of smoothing and tracking that occurs. The more values in the moving average, the greater the amount of smoothing, and therefore the longer it takes the moving average to react to a change in the level of the series.

On the other hand, the fewer values in the moving average, the greater amount of tracking, and therefore the more ...