Robust Long Term Forecasting of Seasonal Time Series

We propose the usage of a simple difference equation for predicting seasonal, trended time series with clear periodicity. By computing several forecasts for different settings of the method’s single free parameter we obtain an ensemble of forecasts. These ensemble is combined to the final forecast by taking the samplewise median of those forecasts that were generated by models showing low prediction errors on left-out parts of the time-series. We show the application of this approach to the Mauna Loa atmospheric carbon dioxide concentration (ACDC) time series.