Cover Image

Hybridization of Ensemble Kalman Filter and Non-linear Auto-regressive Neural Network for Financial Forecasting

Financial data is characterized as non-linear, chaotic in nature and volatile thus making the process of forecasting cumbersome. Therefore, a successful forecasting model must be able to capture longterm dependencies from the past chaotic data. In this study, a novel hybrid model, called UKF-NAR...

Full description

Saved in:
Bibliographic Details
Main Author: Lai, Fong Woon
Other Authors: Rajendra , Prasath
Format: Book Section
Published: Springer 2014
Online Access:http://eprints.utp.edu.my/11587/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utp.eprints.11587
record_format eprints
spelling my.utp.eprints.115872015-04-28T02:54:12Z Hybridization of Ensemble Kalman Filter and Non-linear Auto-regressive Neural Network for Financial Forecasting Lai, Fong Woon Financial data is characterized as non-linear, chaotic in nature and volatile thus making the process of forecasting cumbersome. Therefore, a successful forecasting model must be able to capture longterm dependencies from the past chaotic data. In this study, a novel hybrid model, called UKF-NARX, consists of unscented kalman filter and non-linear auto-regressive network with exogenous input trained with bayesian regulation algorithm is modelled for chaotic financial forecasting. The proposed hybrid model is compared with commonly used Elman-NARX and static forecasting model employed by financial analysts. Experimental results on Bursa Malaysia KLCI data show that the proposed hybrid model outperforms the other two commonly used models. Springer Rajendra , Prasath Philip , O’Reilly Kathirvalavakumar, T. 2014 Book Section PeerReviewed Lai, Fong Woon (2014) Hybridization of Ensemble Kalman Filter and Non-linear Auto-regressive Neural Network for Financial Forecasting. In: Mining Intelligence and Knowledge Exploration. Springer, London, pp. 72-81. ISBN 978-3-319-13816-9 http://eprints.utp.edu.my/11587/
institution Universiti Teknologi Petronas
building UTP Resource Centre
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Petronas
content_source UTP Institutional Repository
url_provider http://eprints.utp.edu.my/
description Financial data is characterized as non-linear, chaotic in nature and volatile thus making the process of forecasting cumbersome. Therefore, a successful forecasting model must be able to capture longterm dependencies from the past chaotic data. In this study, a novel hybrid model, called UKF-NARX, consists of unscented kalman filter and non-linear auto-regressive network with exogenous input trained with bayesian regulation algorithm is modelled for chaotic financial forecasting. The proposed hybrid model is compared with commonly used Elman-NARX and static forecasting model employed by financial analysts. Experimental results on Bursa Malaysia KLCI data show that the proposed hybrid model outperforms the other two commonly used models.
author2 Rajendra , Prasath
author_facet Rajendra , Prasath
Lai, Fong Woon
format Book Section
author Lai, Fong Woon
spellingShingle Lai, Fong Woon
Hybridization of Ensemble Kalman Filter and Non-linear Auto-regressive Neural Network for Financial Forecasting
author_sort Lai, Fong Woon
title Hybridization of Ensemble Kalman Filter and Non-linear Auto-regressive Neural Network for Financial Forecasting
title_short Hybridization of Ensemble Kalman Filter and Non-linear Auto-regressive Neural Network for Financial Forecasting
title_full Hybridization of Ensemble Kalman Filter and Non-linear Auto-regressive Neural Network for Financial Forecasting
title_fullStr Hybridization of Ensemble Kalman Filter and Non-linear Auto-regressive Neural Network for Financial Forecasting
title_full_unstemmed Hybridization of Ensemble Kalman Filter and Non-linear Auto-regressive Neural Network for Financial Forecasting
title_sort hybridization of ensemble kalman filter and non-linear auto-regressive neural network for financial forecasting
publisher Springer
publishDate 2014
url http://eprints.utp.edu.my/11587/
_version_ 1738655965932158976
score 13.18916

Similar Items