Input data preprocessing method for exchange rate forecasting via neural network
The aim of this paper is to present a method for neural network input parameters selection and preprocessing. The purpose of this network is to forecast foreign exchange rates using artificial intelligence. Two data sets are formed for two different economic systems. Each system is represen...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Faculty of Technical Sciences in Cacak
2014-01-01
|
| Series: | Serbian Journal of Electrical Engineering |
| Subjects: | |
| Online Access: | http://www.doiserbia.nb.rs/img/doi/1451-4869/2014/1451-48691404597A.pdf |
| _version_ | 1828741771591417856 |
|---|---|
| author | Antić Dragan S. Milovanović Miroslav B. Perić Staniša Lj. Nikolić Saša S. Milojković Marko T. |
| author_facet | Antić Dragan S. Milovanović Miroslav B. Perić Staniša Lj. Nikolić Saša S. Milojković Marko T. |
| author_sort | Antić Dragan S. |
| collection | DOAJ |
| description | The aim of this paper is to present a method for neural network input
parameters selection and preprocessing. The purpose of this network is to
forecast foreign exchange rates using artificial intelligence. Two data sets
are formed for two different economic systems. Each system is represented by
six categories with 70 economic parameters which are used in the analysis.
Reduction of these parameters within each category was performed by using the
principal component analysis method. Component interdependencies are
established and relations between them are formed. Newly formed relations
were used to create input vectors of a neural network. The multilayer feed
forward neural network is formed and trained using batch training. Finally,
simulation results are presented and it is concluded that input data
preparation method is an effective way for preprocessing neural network data.
[Projekat Ministarstva nauke Republike Srbije, br.TR 35005, br. III 43007 i
br. III 44006] |
| first_indexed | 2024-04-13T01:06:55Z |
| format | Article |
| id | doaj.art-9c02b77b597f4430a3172bc80c69b98e |
| institution | Directory Open Access Journal |
| issn | 1451-4869 2217-7183 |
| language | English |
| last_indexed | 2024-04-13T01:06:55Z |
| publishDate | 2014-01-01 |
| publisher | Faculty of Technical Sciences in Cacak |
| record_format | Article |
| series | Serbian Journal of Electrical Engineering |
| spelling | doaj.art-9c02b77b597f4430a3172bc80c69b98e2022-12-22T03:09:20ZengFaculty of Technical Sciences in CacakSerbian Journal of Electrical Engineering1451-48692217-71832014-01-0111459760810.2298/SJEE1404597A1451-48691404597AInput data preprocessing method for exchange rate forecasting via neural networkAntić Dragan S.0Milovanović Miroslav B.1Perić Staniša Lj.2Nikolić Saša S.3Milojković Marko T.4Faculty of Electronic Engineering, NišFaculty of Electronic Engineering, NišFaculty of Electronic Engineering, NišFaculty of Electronic Engineering, NišFaculty of Electronic Engineering, NišThe aim of this paper is to present a method for neural network input parameters selection and preprocessing. The purpose of this network is to forecast foreign exchange rates using artificial intelligence. Two data sets are formed for two different economic systems. Each system is represented by six categories with 70 economic parameters which are used in the analysis. Reduction of these parameters within each category was performed by using the principal component analysis method. Component interdependencies are established and relations between them are formed. Newly formed relations were used to create input vectors of a neural network. The multilayer feed forward neural network is formed and trained using batch training. Finally, simulation results are presented and it is concluded that input data preparation method is an effective way for preprocessing neural network data. [Projekat Ministarstva nauke Republike Srbije, br.TR 35005, br. III 43007 i br. III 44006]http://www.doiserbia.nb.rs/img/doi/1451-4869/2014/1451-48691404597A.pdfneural networkdatabasesforecastinginput datareduction |
| spellingShingle | Antić Dragan S. Milovanović Miroslav B. Perić Staniša Lj. Nikolić Saša S. Milojković Marko T. Input data preprocessing method for exchange rate forecasting via neural network Serbian Journal of Electrical Engineering neural network databases forecasting input data reduction |
| title | Input data preprocessing method for exchange rate forecasting via neural network |
| title_full | Input data preprocessing method for exchange rate forecasting via neural network |
| title_fullStr | Input data preprocessing method for exchange rate forecasting via neural network |
| title_full_unstemmed | Input data preprocessing method for exchange rate forecasting via neural network |
| title_short | Input data preprocessing method for exchange rate forecasting via neural network |
| title_sort | input data preprocessing method for exchange rate forecasting via neural network |
| topic | neural network databases forecasting input data reduction |
| url | http://www.doiserbia.nb.rs/img/doi/1451-4869/2014/1451-48691404597A.pdf |
| work_keys_str_mv | AT anticdragans inputdatapreprocessingmethodforexchangerateforecastingvianeuralnetwork AT milovanovicmiroslavb inputdatapreprocessingmethodforexchangerateforecastingvianeuralnetwork AT pericstanisalj inputdatapreprocessingmethodforexchangerateforecastingvianeuralnetwork AT nikolicsasas inputdatapreprocessingmethodforexchangerateforecastingvianeuralnetwork AT milojkovicmarkot inputdatapreprocessingmethodforexchangerateforecastingvianeuralnetwork |