Example of Double Exponential Smoothing

An online retailer wants to predict computer sales for the next six months. The retailer collects data on computer sales and software sales from the previous two years to predict future trends.

  1. Open the sample data, ComputerSales.MTW.
  2. Choose Stat > Time Series > Double Exp Smoothing.
  3. In Variable, enter Computer Sales.
  4. Select Generate forecasts. In Number of forecasts, enter 6.
  5. Click OK.

Interpret the results

On this smoothing plot, the fitted values closely follow the actual data. The forecasts predict a slight upward trend in sales for the next 6 months.

Double Exponential Smoothing for Computer Sales

Method Data Computer Sales Length 24
Smoothing Constants α (level) 0.599409 γ (trend) 0.130921
Accuracy Measures MAPE 9 MAD 25814 MSD 1027385418
Forecasts Period Forecast Lower Upper 25 387788 324546 451030 26 393620 318188 469051 27 399452 310644 488260 28 405284 302374 508193 29 411116 293640 528591 30 416948 284595 549300

Double Exponential Smoothing Plot for Computer Sales

By using this site you agree to the use of cookies for analytics and personalized content.  Read our policy