Modeling and forecasting of KLCI weekly return using WT-ANN integrated model

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The forecasting of weekly return is one of the most challenging tasks in investment since the time series are volatile and non-stationary. In this study, an integrated model of wavelet transform and artificial neural network, WT-ANN is studied for modeling and forecasting of KLCI weekly return. First, the WT is applied to decompose the weekly return time series in order to eliminate noise. Then, a mathematical model of the time series is constructed using the ANN. The performance of the suggested model will be evaluated by root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE). The result shows that the WT-ANN model can be considered as a feasible and powerful model for time series modeling and prediction.

Original languageEnglish
Title of host publicationAIP Conference Proceedings
Pages1276-1282
Number of pages7
Volume1522
DOIs
Publication statusPublished - 2013
Event20th National Symposium on Mathematical Sciences - Research in Mathematical Sciences: A Catalyst for Creativity and Innovation, SKSM 2012 - Putrajaya
Duration: 18 Dec 201220 Dec 2012

Other

Other20th National Symposium on Mathematical Sciences - Research in Mathematical Sciences: A Catalyst for Creativity and Innovation, SKSM 2012
CityPutrajaya
Period18/12/1220/12/12

Fingerprint

forecasting
wavelet analysis
mathematical models
predictions

Keywords

  • Artificial neural network
  • Wavelet transform
  • Weekly return

ASJC Scopus subject areas

  • Physics and Astronomy(all)

Cite this

Modeling and forecasting of KLCI weekly return using WT-ANN integrated model. / Liew, Wei Thong; Liong, Choong Yeun; Hussain, Saiful Izzuan; Isa, Zaidi.

AIP Conference Proceedings. Vol. 1522 2013. p. 1276-1282.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Liew, WT, Liong, CY, Hussain, SI & Isa, Z 2013, Modeling and forecasting of KLCI weekly return using WT-ANN integrated model. in AIP Conference Proceedings. vol. 1522, pp. 1276-1282, 20th National Symposium on Mathematical Sciences - Research in Mathematical Sciences: A Catalyst for Creativity and Innovation, SKSM 2012, Putrajaya, 18/12/12. https://doi.org/10.1063/1.4801277
@inproceedings{88a99683fd5a4acf8a1a73aff91017cf,
title = "Modeling and forecasting of KLCI weekly return using WT-ANN integrated model",
abstract = "The forecasting of weekly return is one of the most challenging tasks in investment since the time series are volatile and non-stationary. In this study, an integrated model of wavelet transform and artificial neural network, WT-ANN is studied for modeling and forecasting of KLCI weekly return. First, the WT is applied to decompose the weekly return time series in order to eliminate noise. Then, a mathematical model of the time series is constructed using the ANN. The performance of the suggested model will be evaluated by root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE). The result shows that the WT-ANN model can be considered as a feasible and powerful model for time series modeling and prediction.",
keywords = "Artificial neural network, Wavelet transform, Weekly return",
author = "Liew, {Wei Thong} and Liong, {Choong Yeun} and Hussain, {Saiful Izzuan} and Zaidi Isa",
year = "2013",
doi = "10.1063/1.4801277",
language = "English",
isbn = "9780735411500",
volume = "1522",
pages = "1276--1282",
booktitle = "AIP Conference Proceedings",

}

TY - GEN

T1 - Modeling and forecasting of KLCI weekly return using WT-ANN integrated model

AU - Liew, Wei Thong

AU - Liong, Choong Yeun

AU - Hussain, Saiful Izzuan

AU - Isa, Zaidi

PY - 2013

Y1 - 2013

N2 - The forecasting of weekly return is one of the most challenging tasks in investment since the time series are volatile and non-stationary. In this study, an integrated model of wavelet transform and artificial neural network, WT-ANN is studied for modeling and forecasting of KLCI weekly return. First, the WT is applied to decompose the weekly return time series in order to eliminate noise. Then, a mathematical model of the time series is constructed using the ANN. The performance of the suggested model will be evaluated by root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE). The result shows that the WT-ANN model can be considered as a feasible and powerful model for time series modeling and prediction.

AB - The forecasting of weekly return is one of the most challenging tasks in investment since the time series are volatile and non-stationary. In this study, an integrated model of wavelet transform and artificial neural network, WT-ANN is studied for modeling and forecasting of KLCI weekly return. First, the WT is applied to decompose the weekly return time series in order to eliminate noise. Then, a mathematical model of the time series is constructed using the ANN. The performance of the suggested model will be evaluated by root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE). The result shows that the WT-ANN model can be considered as a feasible and powerful model for time series modeling and prediction.

KW - Artificial neural network

KW - Wavelet transform

KW - Weekly return

UR - http://www.scopus.com/inward/record.url?scp=84876906269&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84876906269&partnerID=8YFLogxK

U2 - 10.1063/1.4801277

DO - 10.1063/1.4801277

M3 - Conference contribution

SN - 9780735411500

VL - 1522

SP - 1276

EP - 1282

BT - AIP Conference Proceedings

ER -