Application of Sliding Window for Financial Time Series Prediction using Time-Delay Neural Networks
This paper proposes application of sliding window technique to time-delay neural network (TDNN) for prediction of financial time series. Neural network is a data-driven approach, in which we have huge data samples but limited information about the model structure. In this paper, we measure performan...
Main Author: | |
---|---|
Format: | Article |
Language: | fas |
Published: |
Allameh Tabataba'i University Press
2015-07-01
|
Series: | Faslnāmah-i Pizhūhish/Nāmah-i Iqtisādī |
Subjects: | |
Online Access: | http://joer.atu.ac.ir/article_1648_de0a3c717335fe6d0cbb72cc915e3947.pdf |
id |
doaj-fa1a54da225b4657864c32965166e6ae |
---|---|
record_format |
Article |
spelling |
doaj-fa1a54da225b4657864c32965166e6ae2020-11-24T21:44:33ZfasAllameh Tabataba'i University PressFaslnāmah-i Pizhūhish/Nāmah-i Iqtisādī1735-210X2015-07-01155775108Application of Sliding Window for Financial Time Series Prediction using Time-Delay Neural NetworksMohammadreza Asghari Oskoei 0Assistant Professor, Department of Mathematics and Computer Science, Allameh Tabataba’i UniversityThis paper proposes application of sliding window technique to time-delay neural network (TDNN) for prediction of financial time series. Neural network is a data-driven approach, in which we have huge data samples but limited information about the model structure. In this paper, we measure performance of the prediction and apply sliding window technique to select the most favorable neural network structure, time-delay taps and the most desirable training data size that result in the best prediction performance. The method was evaluated by using real data of share price of four firms traded in London Stock Exchange. The results show remarkable decrease for the root mean squared error, mean absolute percentage error and the linear regression of TDNN output offset. http://joer.atu.ac.ir/article_1648_de0a3c717335fe6d0cbb72cc915e3947.pdfTime Series Prediction; Time-Delay Neural Networks; Sliding Window; Prediction Errors |
collection |
DOAJ |
language |
fas |
format |
Article |
sources |
DOAJ |
author |
Mohammadreza Asghari Oskoei |
spellingShingle |
Mohammadreza Asghari Oskoei Application of Sliding Window for Financial Time Series Prediction using Time-Delay Neural Networks Faslnāmah-i Pizhūhish/Nāmah-i Iqtisādī Time Series Prediction; Time-Delay Neural Networks; Sliding Window; Prediction Errors |
author_facet |
Mohammadreza Asghari Oskoei |
author_sort |
Mohammadreza Asghari Oskoei |
title |
Application of Sliding Window for Financial Time Series Prediction using Time-Delay Neural Networks |
title_short |
Application of Sliding Window for Financial Time Series Prediction using Time-Delay Neural Networks |
title_full |
Application of Sliding Window for Financial Time Series Prediction using Time-Delay Neural Networks |
title_fullStr |
Application of Sliding Window for Financial Time Series Prediction using Time-Delay Neural Networks |
title_full_unstemmed |
Application of Sliding Window for Financial Time Series Prediction using Time-Delay Neural Networks |
title_sort |
application of sliding window for financial time series prediction using time-delay neural networks |
publisher |
Allameh Tabataba'i University Press |
series |
Faslnāmah-i Pizhūhish/Nāmah-i Iqtisādī |
issn |
1735-210X |
publishDate |
2015-07-01 |
description |
This paper proposes application of sliding window technique to time-delay neural network (TDNN) for prediction of financial time series. Neural network is a data-driven approach, in which we have huge data samples but limited information about the model structure. In this paper, we measure performance of the prediction and apply sliding window technique to select the most favorable neural network structure, time-delay taps and the most desirable training data size that result in the best prediction performance. The method was evaluated by using real data of share price of four firms traded in London Stock Exchange. The results show remarkable decrease for the root mean squared error, mean absolute percentage error and the linear regression of TDNN output offset.
|
topic |
Time Series Prediction; Time-Delay Neural Networks; Sliding Window; Prediction Errors |
url |
http://joer.atu.ac.ir/article_1648_de0a3c717335fe6d0cbb72cc915e3947.pdf |
work_keys_str_mv |
AT mohammadrezaasgharioskoei applicationofslidingwindowforfinancialtimeseriespredictionusingtimedelayneuralnetworks |
_version_ |
1725909542417465344 |