An adaptive neuro-fuzzy inference system for modelling Australia's regional airline passenger demand

This study has proposed and empirically tested for the first time two adaptive neuro-fuzzy inference system (ANFIS) models for forecasting Australia's regional airline passenger demand, as measured by enplaned passengers (PAX model) and revenue passenger kilometres performed (RPKs model). In ANFIS, both the learning capabilities of an artificial neural network (ANN) and the reasoning capabilities of fuzzy logic are combined to provide enhanced prediction capabilities, as compared to using a single methodology. Sugeno fuzzy rules were used in the ANFIS structure and Gaussian membership function and linear membership functions were also developed. The hybrid learning algorithm and the subtractive clustering partition method were used to generate the optimum ANFIS models. Data was normalised in order to increase the model's training performance. The results found that the mean absolute percentage error (MAPE) for the out of sample testing dataset of the PAX and RPKs models was 5.40% and 6.91%, respectively.