Do Dynamic Neural Networks Stand a Better Chance in Fractionally Integrated Process Forecasting?
The main purpose of the present study was to investigate the capabilities of two generations of models such as those based on dynamic neural network (e.g., Nonlinear Neural network Auto Regressive or NNAR model) and a regressive (Auto Regressive Fractionally Integrated Moving Average model which is...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
EconJournals
2013-06-01
|
Series: | International Journal of Economics and Financial Issues |
Subjects: | |
Online Access: | https://dergipark.org.tr/tr/pub/ijefi/issue/31957/351921?publisher=http-www-cag-edu-tr-ilhan-ozturk |
id |
doaj-628f729768314e6eb61f1b9cfc787de6 |
---|---|
record_format |
Article |
spelling |
doaj-628f729768314e6eb61f1b9cfc787de62020-11-25T01:44:26ZengEconJournalsInternational Journal of Economics and Financial Issues2146-41382013-06-01324664751032Do Dynamic Neural Networks Stand a Better Chance in Fractionally Integrated Process Forecasting?Majid DelavariNadiya Gandali AlikhaniEsmaeil NaderiThe main purpose of the present study was to investigate the capabilities of two generations of models such as those based on dynamic neural network (e.g., Nonlinear Neural network Auto Regressive or NNAR model) and a regressive (Auto Regressive Fractionally Integrated Moving Average model which is based on Fractional Integration Approach) in forecasting daily data related to the return index of Tehran Stock Exchange (TSE). In order to compare these models under similar conditions, Mean Square Error (MSE) and also Root Mean Square Error (RMSE) were selected as criteria for the models’ simulated out-of-sample forecasting performance. Besides, fractal markets hypothesis was examined and according to the findings, fractal structure was confirmed to exist in the time series under investigation. Another finding of the study was that dynamic artificial neural network model had the best performance in out-of-sample forecasting based on the criteria introduced for calculating forecasting error in comparison with the ARFIMA model.https://dergipark.org.tr/tr/pub/ijefi/issue/31957/351921?publisher=http-www-cag-edu-tr-ilhan-ozturkstock return forecasting long memory nnar arfima |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Majid Delavari Nadiya Gandali Alikhani Esmaeil Naderi |
spellingShingle |
Majid Delavari Nadiya Gandali Alikhani Esmaeil Naderi Do Dynamic Neural Networks Stand a Better Chance in Fractionally Integrated Process Forecasting? International Journal of Economics and Financial Issues stock return forecasting long memory nnar arfima |
author_facet |
Majid Delavari Nadiya Gandali Alikhani Esmaeil Naderi |
author_sort |
Majid Delavari |
title |
Do Dynamic Neural Networks Stand a Better Chance in Fractionally Integrated Process Forecasting? |
title_short |
Do Dynamic Neural Networks Stand a Better Chance in Fractionally Integrated Process Forecasting? |
title_full |
Do Dynamic Neural Networks Stand a Better Chance in Fractionally Integrated Process Forecasting? |
title_fullStr |
Do Dynamic Neural Networks Stand a Better Chance in Fractionally Integrated Process Forecasting? |
title_full_unstemmed |
Do Dynamic Neural Networks Stand a Better Chance in Fractionally Integrated Process Forecasting? |
title_sort |
do dynamic neural networks stand a better chance in fractionally integrated process forecasting? |
publisher |
EconJournals |
series |
International Journal of Economics and Financial Issues |
issn |
2146-4138 |
publishDate |
2013-06-01 |
description |
The main purpose of the present study was to investigate the capabilities of two generations of models such as those based on dynamic neural network (e.g., Nonlinear Neural network Auto Regressive or NNAR model) and a regressive (Auto Regressive Fractionally Integrated Moving Average model which is based on Fractional Integration Approach) in forecasting daily data related to the return index of Tehran Stock Exchange (TSE). In order to compare these models under similar conditions, Mean Square Error (MSE) and also Root Mean Square Error (RMSE) were selected as criteria for the models’ simulated out-of-sample forecasting performance. Besides, fractal markets hypothesis was examined and according to the findings, fractal structure was confirmed to exist in the time series under investigation. Another finding of the study was that dynamic artificial neural network model had the best performance in out-of-sample forecasting based on the criteria introduced for calculating forecasting error in comparison with the ARFIMA model. |
topic |
stock return forecasting long memory nnar arfima |
url |
https://dergipark.org.tr/tr/pub/ijefi/issue/31957/351921?publisher=http-www-cag-edu-tr-ilhan-ozturk |
work_keys_str_mv |
AT majiddelavari dodynamicneuralnetworksstandabetterchanceinfractionallyintegratedprocessforecasting AT nadiyagandalialikhani dodynamicneuralnetworksstandabetterchanceinfractionallyintegratedprocessforecasting AT esmaeilnaderi dodynamicneuralnetworksstandabetterchanceinfractionallyintegratedprocessforecasting |
_version_ |
1725028693459337216 |