An Artificial Neural Network for Data Forecasting Purposes
Considering the fact that markets are generally influenced by different external factors, the stock market prediction is one of the most difficult tasks of time series analysis. The research reported in this paper aims to investigate the potential of artificial neural networks (ANN) in solving the f...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Inforec Association
2015-01-01
|
| Series: | Informatică economică |
| Subjects: | |
| Online Access: | http://revistaie.ase.ro/content/74/04%20-%20cocianu,%20grigoryan.pdf |
| _version_ | 1819263164511944704 |
|---|---|
| author | Catalina Lucia COCIANU Hakob GRIGORYAN |
| author_facet | Catalina Lucia COCIANU Hakob GRIGORYAN |
| author_sort | Catalina Lucia COCIANU |
| collection | DOAJ |
| description | Considering the fact that markets are generally influenced by different external factors, the stock market prediction is one of the most difficult tasks of time series analysis. The research reported in this paper aims to investigate the potential of artificial neural networks (ANN) in solving the forecast task in the most general case, when the time series are non-stationary. We used a feed-forward neural architecture: the nonlinear autoregressive network with exogenous inputs. The network training function used to update the weight and bias parameters corresponds to gradient descent with adaptive learning rate variant of the backpropagation algorithm. The results obtained using this technique are compared with the ones resulted from some ARIMA models. We used the mean square error (MSE) measure to evaluate the performances of these two models. The comparative analysis leads to the conclusion that the proposed model can be successfully applied to forecast the financial data. |
| first_indexed | 2024-12-23T20:09:14Z |
| format | Article |
| id | doaj.art-04037efad9484146beeffada2a41e183 |
| institution | Directory Open Access Journal |
| issn | 1453-1305 1842-8088 |
| language | English |
| last_indexed | 2024-12-23T20:09:14Z |
| publishDate | 2015-01-01 |
| publisher | Inforec Association |
| record_format | Article |
| series | Informatică economică |
| spelling | doaj.art-04037efad9484146beeffada2a41e1832022-12-21T17:32:51ZengInforec AssociationInformatică economică1453-13051842-80882015-01-01192344510.12948/issn14531305/19.2.2015.04An Artificial Neural Network for Data Forecasting PurposesCatalina Lucia COCIANUHakob GRIGORYANConsidering the fact that markets are generally influenced by different external factors, the stock market prediction is one of the most difficult tasks of time series analysis. The research reported in this paper aims to investigate the potential of artificial neural networks (ANN) in solving the forecast task in the most general case, when the time series are non-stationary. We used a feed-forward neural architecture: the nonlinear autoregressive network with exogenous inputs. The network training function used to update the weight and bias parameters corresponds to gradient descent with adaptive learning rate variant of the backpropagation algorithm. The results obtained using this technique are compared with the ones resulted from some ARIMA models. We used the mean square error (MSE) measure to evaluate the performances of these two models. The comparative analysis leads to the conclusion that the proposed model can be successfully applied to forecast the financial data.http://revistaie.ase.ro/content/74/04%20-%20cocianu,%20grigoryan.pdfNeural NetworkNonlinear Autoregressive NetworkExogenous InputsTime SeriesARIMA Model |
| spellingShingle | Catalina Lucia COCIANU Hakob GRIGORYAN An Artificial Neural Network for Data Forecasting Purposes Informatică economică Neural Network Nonlinear Autoregressive Network Exogenous Inputs Time Series ARIMA Model |
| title | An Artificial Neural Network for Data Forecasting Purposes |
| title_full | An Artificial Neural Network for Data Forecasting Purposes |
| title_fullStr | An Artificial Neural Network for Data Forecasting Purposes |
| title_full_unstemmed | An Artificial Neural Network for Data Forecasting Purposes |
| title_short | An Artificial Neural Network for Data Forecasting Purposes |
| title_sort | artificial neural network for data forecasting purposes |
| topic | Neural Network Nonlinear Autoregressive Network Exogenous Inputs Time Series ARIMA Model |
| url | http://revistaie.ase.ro/content/74/04%20-%20cocianu,%20grigoryan.pdf |
| work_keys_str_mv | AT catalinaluciacocianu anartificialneuralnetworkfordataforecastingpurposes AT hakobgrigoryan anartificialneuralnetworkfordataforecastingpurposes AT catalinaluciacocianu artificialneuralnetworkfordataforecastingpurposes AT hakobgrigoryan artificialneuralnetworkfordataforecastingpurposes |