We aimed to forecast demand fluctuations in the hotel business that lead to crises and create a systematic and dynamic process that could be re-used. We forecasted demand for a five star hotel in Ankara using 149 monthly series of data and compared the results with those from MA, Simple, Holt's, Winter's Exponential Smoothing and ARIMA using error measures. Two Delphi-based inquiry panels were used: The Variables Determination Panel and The Environmental Monitoring Panel. The opinions of the second group of panelists were used to adjust Winter's Multiplicative forecasts with an AHP-based approach. We showed that if this forecasting and adjustment process is applied to a hotel monthly, it can be used to predict demand and help the management avoid crises arising from demand fluctuations in their business. The most important characteristic of the model is that it can accommodate change and be further refined in the future. (C) 2007 Elsevier Ltd. All rights reserved.