Using Machine Learning Approaches: to Forecast Airport Air Passenger Demand Key Theories and Cases

Highly accurate and reliable passenger air travel demand forecasts are critical for airports as they are a key input into airport master plans and they are also used to guide management decisions on airport design and infrastructure planning, airport operations, and resource planning. The objective of this book is to develop and empirically test adaptive neuro-fuzzy inference system (ANFIS) and artificial neural networks (ANNs) to predict airport’s passenger demand. The study is based on five major airports: Frankfurt Airport, Hong Kong International Airport, Tokyo’s Narita International Airport, Chicago’s O’Hare International Airport, and Sydney Kingsford Smith Airport, Australia. The performance of the artificial neural network (ANN) and adaptive neuro-fuzzy inference systems models was assessed by five goodness of fit measures: coefficient of determination (R2), mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean squared error (RMSE). Artificial intelligence-based machine learning modelling techniques are worthy of consideration for those interested in forecasting airport passenger demand. Read more