Limits...
Forecasting Natural Gas Prices Using Wavelets, Time Series, and Artificial Neural Networks.

Jin J, Kim J - PLoS ONE (2015)

Bottom Line: We also emphasize the boundary problem in wavelet decomposition, and compare results that consider the boundary problem case with those that do not.The empirical results show that our suggested approach can handle the boundary problem, such that it facilitates the extraction of the appropriate forecasting results.The performance of the wavelet-hybrid approach was superior in all cases, whereas the application of detail components in the forecasting was only able to yield a small improvement in forecasting performance.

View Article: PubMed Central - PubMed

Affiliation: Department of Natural Resources and Environmental Engineering, Hanyang University, Seoul, Korea.

ABSTRACT
Following the unconventional gas revolution, the forecasting of natural gas prices has become increasingly important because the association of these prices with those of crude oil has weakened. With this as motivation, we propose some modified hybrid models in which various combinations of the wavelet approximation, detail components, autoregressive integrated moving average, generalized autoregressive conditional heteroskedasticity, and artificial neural network models are employed to predict natural gas prices. We also emphasize the boundary problem in wavelet decomposition, and compare results that consider the boundary problem case with those that do not. The empirical results show that our suggested approach can handle the boundary problem, such that it facilitates the extraction of the appropriate forecasting results. The performance of the wavelet-hybrid approach was superior in all cases, whereas the application of detail components in the forecasting was only able to yield a small improvement in forecasting performance. Therefore, forecasting with only an approximation component would be acceptable, in consideration of forecasting efficiency.

No MeSH data available.


Flowchart of multilayered perceptron back-propagation neural networks.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4635006&req=5

pone.0142064.g004: Flowchart of multilayered perceptron back-propagation neural networks.

Mentions: ANN is a mathematical model that imitates the human brain to solve problems. Because ANN has the ability to train itself under various circumstances, various fields such as finance and marketing make use of this method [36, 45–47]. In this study, multilayered perceptrons (MLP) are used as a forecasting model, and back propagation is used as a training algorithm. MLP is a layered feed forward network that is trained by static back propagation. Each perceptron has several inputs, and one output that is a nonlinear function of the inputs. Back propagation algorithms are most frequently used in the MLP model. Back propagation modifies the connection strength between the output nodes and the inner nodes. There are several advantages to this method. It is easy to use, and it can model any type of data. Its disadvantages are that the time taken for training is longer than that of other methods, and that it requires large amounts of training data. In short, networks with one hidden layer are capable of approximating any continuous functional mapping, if the number of hidden units is sufficiently large. The flow of the algorithm used in this paper is presented in Fig 4. The numbers of inputs, outputs, and hidden nodes are selected empirically, or by the Akaike informative criterion.


Forecasting Natural Gas Prices Using Wavelets, Time Series, and Artificial Neural Networks.

Jin J, Kim J - PLoS ONE (2015)

Flowchart of multilayered perceptron back-propagation neural networks.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4635006&req=5

pone.0142064.g004: Flowchart of multilayered perceptron back-propagation neural networks.
Mentions: ANN is a mathematical model that imitates the human brain to solve problems. Because ANN has the ability to train itself under various circumstances, various fields such as finance and marketing make use of this method [36, 45–47]. In this study, multilayered perceptrons (MLP) are used as a forecasting model, and back propagation is used as a training algorithm. MLP is a layered feed forward network that is trained by static back propagation. Each perceptron has several inputs, and one output that is a nonlinear function of the inputs. Back propagation algorithms are most frequently used in the MLP model. Back propagation modifies the connection strength between the output nodes and the inner nodes. There are several advantages to this method. It is easy to use, and it can model any type of data. Its disadvantages are that the time taken for training is longer than that of other methods, and that it requires large amounts of training data. In short, networks with one hidden layer are capable of approximating any continuous functional mapping, if the number of hidden units is sufficiently large. The flow of the algorithm used in this paper is presented in Fig 4. The numbers of inputs, outputs, and hidden nodes are selected empirically, or by the Akaike informative criterion.

Bottom Line: We also emphasize the boundary problem in wavelet decomposition, and compare results that consider the boundary problem case with those that do not.The empirical results show that our suggested approach can handle the boundary problem, such that it facilitates the extraction of the appropriate forecasting results.The performance of the wavelet-hybrid approach was superior in all cases, whereas the application of detail components in the forecasting was only able to yield a small improvement in forecasting performance.

View Article: PubMed Central - PubMed

Affiliation: Department of Natural Resources and Environmental Engineering, Hanyang University, Seoul, Korea.

ABSTRACT
Following the unconventional gas revolution, the forecasting of natural gas prices has become increasingly important because the association of these prices with those of crude oil has weakened. With this as motivation, we propose some modified hybrid models in which various combinations of the wavelet approximation, detail components, autoregressive integrated moving average, generalized autoregressive conditional heteroskedasticity, and artificial neural network models are employed to predict natural gas prices. We also emphasize the boundary problem in wavelet decomposition, and compare results that consider the boundary problem case with those that do not. The empirical results show that our suggested approach can handle the boundary problem, such that it facilitates the extraction of the appropriate forecasting results. The performance of the wavelet-hybrid approach was superior in all cases, whereas the application of detail components in the forecasting was only able to yield a small improvement in forecasting performance. Therefore, forecasting with only an approximation component would be acceptable, in consideration of forecasting efficiency.

No MeSH data available.