Weatherford, Larry R.Kimes, Sheryl E.2020-09-122020-09-122003-09-017822587https://hdl.handle.net/1813/72130The arrivals forecast is one of the key inputs for a successful hotel revenue management system, but no research on the best forecasting method has been conducted. In this research, we used data from Choice Hotels and Marriott Hotels to test a variety of forecasting methods and to determine the most accurate method. Preliminary results using the Choice Hotel data show that pickup methods and regression produced the lowest error, while the booking curve and combination forecasts produced fairly inaccurate results. The more in-depth study using the Marriott Hotel data showed that exponential smoothing, pickup, and moving average models were the most robust.en-USRequired Publisher Statement: © Elsevier. Final version published as: Weatherford, L. R., & Kimes, S. E. (2003). A comparison of forecasting methods for hotel revenue management. International Journal of Forecasting, 19(3), 401-415. doi:10.1016/S0169-2070(02)00011-0.This version of the work is released under at Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. Reprinted with permission. All rights reserved.forecasting competitionsforecasting practicecomparative methodstime seriesunivariate: exponential smoothingholt-wintersregressionarticle