Abstract:This study focuses on predicting Australia's low cost carrier passenger demand and revenue passenger kilometres performed (RPKs) using traditional econometric and artificial neural network (ANN) modelling methods. For model development, Australia's real GDP, real GDP per capita, air fares, Australia's population and unemployment, tourism (bed spaces) and 4 dummy variables, utilizing quarterly data obtained between 2002 and 2012, were selected as model parameters. The neural network used multi-layer perceptron … Show more
“…Over-fitting can lead to predictions that are beyond the range of the training data (Richter and Weber, 2013). To avoid model over-fitting, the collected data was randomly divided into a 70:15:15 ratio (Garrido et al, 2014;Kunt et al, 2011;Srisaeng et al, 2015). A cross validation process was carried out during the training phase to avoid over-fitting of the proposed model (Efendigil et al, 2009).…”
Section: Training and Testing The Artificial Neural Networkmentioning
confidence: 99%
“…The stopping criterion was the mean square error (MSE) of the estimated demand with respect to the samples belonging to the validation set. The validation set was not used in adapting the weight vectors of the neural estimator, and was therefore able to detect over-fitting in the training phase (Alekseev and Seixas, 2009;Srisaeng et al, 2015).…”
Section: Training and Testing The Artificial Neural Networkmentioning
confidence: 99%
“…For estimating the generalization capacity of the ANN forecasting model, a testing set was also used (Srisaeng et al, 2015). Thus, after the training process was completed, a testing process was applied to ensure the model accuracy was sufficiently reliable.…”
Section: Training and Testing The Artificial Neural Networkmentioning
confidence: 99%
“…The artificial neural network model is characterized by a network of three layers: input, output and hidden layers (Cocchi et al, 2017;Khan et al, 2015;Srisaeng et al, 2015). An ANN consists of a large number of simple processing elements called neurons.…”
Section: Introductionmentioning
confidence: 99%
“…The ANNs output layer provides the model's predicted values (Kar et al, 2015;Lahmiri and Gagnon, 2015). The number of neurons in the input layer is equal to the number of input variables or independent variables, and the number of output neurons is equal to the number of output variable(s) or dependent variable(s) (Srisaeng et al, 2015;Tiryaki and Aydın, 2014).…”
Abstract:In this paper an Artificial Neural Network (ANN) is proposed for predicting Australia's annual export air cargo demand. The modelling in the study was based on annual data from 1993 to 2016. The ANN model was developed using the input parameters of world real merchandise exports, world population growth, world jet fuel prices, world air cargo yields (proxy for air cargo costs), outbound flights from Australia, and Australian/ United States dollar exchange rate and two dummy variables, which controlled for the strong cyclical fluctuations in air cargo demand which occurred in 2003 and 2015. The artificial neural network (ANN) used multi-layer perceptron (MLP) architecture that compromised a multi-layer feed-forward network and the sigmoid and linear functions were used as activation functions with the feed forward-back propagation algorithm. The ANN was applied during training, testing and validation and had 8 inputs, 1 neuron in the hidden layer and 1 neuron in the output layer. The data was randomly divided into three data sets; training, testing and model validation. The best-fit model was selected according to four goodness-of-fit measures: mean absolute error (MAE), mean square error (MSE), root mean square errors (RMSE), and mean absolute percentage errors (MAPE). The highest R-value obtained from the ANN model is 0.97844. The results suggest that the ANN model is an efficient tool for predicting Australia's annual export air cargo demand.
“…Over-fitting can lead to predictions that are beyond the range of the training data (Richter and Weber, 2013). To avoid model over-fitting, the collected data was randomly divided into a 70:15:15 ratio (Garrido et al, 2014;Kunt et al, 2011;Srisaeng et al, 2015). A cross validation process was carried out during the training phase to avoid over-fitting of the proposed model (Efendigil et al, 2009).…”
Section: Training and Testing The Artificial Neural Networkmentioning
confidence: 99%
“…The stopping criterion was the mean square error (MSE) of the estimated demand with respect to the samples belonging to the validation set. The validation set was not used in adapting the weight vectors of the neural estimator, and was therefore able to detect over-fitting in the training phase (Alekseev and Seixas, 2009;Srisaeng et al, 2015).…”
Section: Training and Testing The Artificial Neural Networkmentioning
confidence: 99%
“…For estimating the generalization capacity of the ANN forecasting model, a testing set was also used (Srisaeng et al, 2015). Thus, after the training process was completed, a testing process was applied to ensure the model accuracy was sufficiently reliable.…”
Section: Training and Testing The Artificial Neural Networkmentioning
confidence: 99%
“…The artificial neural network model is characterized by a network of three layers: input, output and hidden layers (Cocchi et al, 2017;Khan et al, 2015;Srisaeng et al, 2015). An ANN consists of a large number of simple processing elements called neurons.…”
Section: Introductionmentioning
confidence: 99%
“…The ANNs output layer provides the model's predicted values (Kar et al, 2015;Lahmiri and Gagnon, 2015). The number of neurons in the input layer is equal to the number of input variables or independent variables, and the number of output neurons is equal to the number of output variable(s) or dependent variable(s) (Srisaeng et al, 2015;Tiryaki and Aydın, 2014).…”
Abstract:In this paper an Artificial Neural Network (ANN) is proposed for predicting Australia's annual export air cargo demand. The modelling in the study was based on annual data from 1993 to 2016. The ANN model was developed using the input parameters of world real merchandise exports, world population growth, world jet fuel prices, world air cargo yields (proxy for air cargo costs), outbound flights from Australia, and Australian/ United States dollar exchange rate and two dummy variables, which controlled for the strong cyclical fluctuations in air cargo demand which occurred in 2003 and 2015. The artificial neural network (ANN) used multi-layer perceptron (MLP) architecture that compromised a multi-layer feed-forward network and the sigmoid and linear functions were used as activation functions with the feed forward-back propagation algorithm. The ANN was applied during training, testing and validation and had 8 inputs, 1 neuron in the hidden layer and 1 neuron in the output layer. The data was randomly divided into three data sets; training, testing and model validation. The best-fit model was selected according to four goodness-of-fit measures: mean absolute error (MAE), mean square error (MSE), root mean square errors (RMSE), and mean absolute percentage errors (MAPE). The highest R-value obtained from the ANN model is 0.97844. The results suggest that the ANN model is an efficient tool for predicting Australia's annual export air cargo demand.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.