Using forecasting techniques to predict meal demand in Title IIIc congregate lunch programs.
The purpose of this study was to determine which forecasting model would most accurately predict meal demand in Title IIIc congregate lunch programs designed for serving older adults. Forecasting techniques including naïve, moving average (three versions) and simple exponential smoothing were applied to data collected over a 4-month period from seven meal sites located in a large urban area. An analysis of the forecasting models using mean absolute deviations and mean squared errors indicated that simple mathematical forecasting techniques provided better predictions of meal demand than did the naïve method for all sites. In four of the seven sites, exponential smoothing was the best forecasting model, whereas in the remaining sites, moving average models provided the best forecast. Implications are discussed.