Room occupancy rate forecasting: a neural network approach

Experimental results indicate that using neural networks to forecast room occupancy rates outperforms multiple regression and naive extrapolation, two commonly used forecasting approaches.

Abstract

In recent years, neural networks have become popular in the scientific and business fields. In the hotel industry, researchers have recently devoted attention to the application of neural networks to the classification of tourist segments and the prediction of visitor behaviour. However, no previous attempt has been made to incorporate neural networks into hotel occupancy rate forecasting. This paper reports on a study about applying neural networks to the forecasting of room occupancy rates. The significance of this approach was tested with actual data from the Hong Kong hotel industry. Estimated room occupancy rates were compared with actual room occupancy rates. Experimental results indicate that using neural networks to forecast room occupancy rates outperforms multiple regression and naïve extrapolation, two commonly used forecasting approaches.