This book discusses the practice of flight overbooking within the context of airline revenue management and provides a novel solution using artificial neural network (ANN) to better predict the number of passenger no-shows for a particular flight. The performance of the ANN forecasting method is compared to more traditional time series seasonal forecasting methods of Autoregressive Integrated Moving Average (ARIMA) and the Kalman Filter. Using actual passenger no-show data, the prediction accuracy of all models is evaluated using established statistical error measures. The approach and methods discussed in this book can be applied to other types of businesses that deals with perishable commodities or where overbooking is practiced.
Number of pages: 262