Further results on focus forecasting vs. exponential smoothing

In an earlier paper, we found that damped-trend, seasonal exponential smoothing was more accurate than a simple version of Focus Forecasting, based on Flores and Whybark. This note tests Demand Solutions, a more sophisticated version of Focus Forecasting. As in the earlier paper, we used five time series of cookware demand from a production planning application and 91 time series from the M-Competition study of forecast accuracy. Results are much the same as in our earlier paper. Exponential smoothing is substantially more accurate than Demand Solutions. This is perhaps not surprising in that Demand Solutions' forecasting rules are arbitrary, with no statistical rationale. Users of Focus Forecasting have much to gain by adopting statistical forecasting methods.