An Adaptive Neuro-Fuzzy Inference System for the Prediction of Kansai International Airport Domestic Passenger Demand

This paper proposes an adaptive neuro-fuzzy inference system for predicting an airport’s domestic air passenger demand. Osaka’s Kansai International Airport was selected as the case site for the study, which covered the period 1994 to 2018. The combination of an artificial neural network with a fuzzy inference system provides a hybrid neuro fuzzy inference system that can predict an airport’s domestic air passenger demand with a high predictive capability. In this study, coefficient of determination (R²-value), root mean square errors (RMSE), mean absolute errors (MAE) and the mean absolute percentage error (MAPE) were used to test the performance of the proposed ANFIS model. The mean absolute percentage error (MAPE) for the overall data set of the model was 5.15%. The highest R²-value in the modelling was around 0.9742, which suggests that the ANFIS is an efficient model for predicting Kansai International Airport’s domestic passenger demand.