A comparison of time series and econometric models for forecasting restaurant sales

Historically, forecasting of restaurant sales in the hospitality industry has been 'judgementally' based. Given the importance of both short-term and long-term sales forecasts for effective restaurant management, we have investigated various forecasting models for accuracy and efficiency. The results of the study show that for the actual restaurant sales in this sample, time series models (specifically Box-Jenkins and exponential smoothing models) performed as well or better in forecasting sales than an econometric model. Since time series models (especially exponential smoothing models) are typically more economical in terms of time and skill levels of the users, the results of this study have important implications for the use of forecasting techniques in the restaurant industry.