TIME SERIES FORECASTING USING NEURAL NETWORKS
Recent studies have shown the classification and prediction power of the Neural Networks. It has been demonstrated that a NN can approximate any continuous function. Neural networks have been successfully used for forecasting of financial data series. The classical methods used for time series predi...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nicolae Titulescu University Publishing House
2013-05-01
|
| Series: | Challenges of the Knowledge Society |
| Subjects: | |
| Online Access: | http://cks.univnt.ro/uploads/cks_2013_articles/index.php?dir=4_IT_in_Social_Sciences%2F&download=cks_2013_it_002.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846093141288943616 |
|---|---|
| author | BOGDAN OANCEA ŞTEFAN CRISTIAN CIUCU |
| author_facet | BOGDAN OANCEA ŞTEFAN CRISTIAN CIUCU |
| author_sort | BOGDAN OANCEA |
| collection | DOAJ |
| description | Recent studies have shown the classification and prediction power of the Neural Networks. It has been demonstrated that a NN can approximate any continuous function. Neural networks have been successfully used for forecasting of financial data series. The classical methods used for time series prediction like Box-Jenkins or ARIMA assumes that there is a linear relationship between inputs and outputs. Neural Networks have the advantage that can approximate nonlinear functions. In this paper we compared the performances of different feed forward and recurrent neural networks and training algorithms for predicting the exchange rate EUR/RON and USD/RON. We used data series with daily exchange rates starting from 2005 until 2013. |
| format | Article |
| id | doaj-art-3e58e7ca71fa4369ae13367ab3e98e97 |
| institution | Kabale University |
| issn | 2068-7796 2068-7796 |
| language | English |
| publishDate | 2013-05-01 |
| publisher | Nicolae Titulescu University Publishing House |
| record_format | Article |
| series | Challenges of the Knowledge Society |
| spelling | doaj-art-3e58e7ca71fa4369ae13367ab3e98e972025-01-02T18:49:14ZengNicolae Titulescu University Publishing HouseChallenges of the Knowledge Society2068-77962068-77962013-05-013-14021408TIME SERIES FORECASTING USING NEURAL NETWORKSBOGDAN OANCEA0ŞTEFAN CRISTIAN CIUCU1Professor, PhD, “Nicolae Titulescu” University of Bucharest (email: bogdan.oancea@gmail.com).IT Director, “Nicolae Titulescu” University (email: stefanciucu@yahoo.com).Recent studies have shown the classification and prediction power of the Neural Networks. It has been demonstrated that a NN can approximate any continuous function. Neural networks have been successfully used for forecasting of financial data series. The classical methods used for time series prediction like Box-Jenkins or ARIMA assumes that there is a linear relationship between inputs and outputs. Neural Networks have the advantage that can approximate nonlinear functions. In this paper we compared the performances of different feed forward and recurrent neural networks and training algorithms for predicting the exchange rate EUR/RON and USD/RON. We used data series with daily exchange rates starting from 2005 until 2013.http://cks.univnt.ro/uploads/cks_2013_articles/index.php?dir=4_IT_in_Social_Sciences%2F&download=cks_2013_it_002.pdfneural networkstime seriesforecastingexchange ratepredicting |
| spellingShingle | BOGDAN OANCEA ŞTEFAN CRISTIAN CIUCU TIME SERIES FORECASTING USING NEURAL NETWORKS Challenges of the Knowledge Society neural networks time series forecasting exchange rate predicting |
| title | TIME SERIES FORECASTING USING NEURAL NETWORKS |
| title_full | TIME SERIES FORECASTING USING NEURAL NETWORKS |
| title_fullStr | TIME SERIES FORECASTING USING NEURAL NETWORKS |
| title_full_unstemmed | TIME SERIES FORECASTING USING NEURAL NETWORKS |
| title_short | TIME SERIES FORECASTING USING NEURAL NETWORKS |
| title_sort | time series forecasting using neural networks |
| topic | neural networks time series forecasting exchange rate predicting |
| url | http://cks.univnt.ro/uploads/cks_2013_articles/index.php?dir=4_IT_in_Social_Sciences%2F&download=cks_2013_it_002.pdf |
| work_keys_str_mv | AT bogdanoancea timeseriesforecastingusingneuralnetworks AT stefancristianciucu timeseriesforecastingusingneuralnetworks |