Volatility forecasting of financial time series using wavelet based exponential generalized autoregressive conditional heteroscedasticity model

Research output: Contribution to journalArticle

Abstract

An improved forecasting model by merging two different computational models in predicting future volatility was proposed. The model integrates wavelet and EGARCH model where the pre-processing activity based on wavelet transform is performed with de-noising technique to eliminate noise in observed signal. The denoised signal is then feed into EGARCH model to forecast the volatility. The predictive capability of the proposed model is compared with the existing EGARCH model. The results show that the hybrid model has increased the accuracy of forecasting future volatility.

Original languageEnglish
JournalCommunications in Statistics - Theory and Methods
DOIs
Publication statusAccepted/In press - 1 Jan 2018

Fingerprint

Volatility Forecasting
Financial Time Series
Generalized Autoregressive Conditional Heteroscedasticity
Wavelets
Volatility
Forecasting
Model
Hybrid Model
Denoising
Merging
Computational Model
Wavelet Transform
Preprocessing
Forecast
Eliminate
Integrate

Keywords

  • de-noising
  • EGARCH model
  • volatility
  • Wavelet transform

ASJC Scopus subject areas

  • Statistics and Probability

Cite this

@article{37a57d89be9a404994b37dcfc33a3c0d,
title = "Volatility forecasting of financial time series using wavelet based exponential generalized autoregressive conditional heteroscedasticity model",
abstract = "An improved forecasting model by merging two different computational models in predicting future volatility was proposed. The model integrates wavelet and EGARCH model where the pre-processing activity based on wavelet transform is performed with de-noising technique to eliminate noise in observed signal. The denoised signal is then feed into EGARCH model to forecast the volatility. The predictive capability of the proposed model is compared with the existing EGARCH model. The results show that the hybrid model has increased the accuracy of forecasting future volatility.",
keywords = "de-noising, EGARCH model, volatility, Wavelet transform",
author = "Mohammed, {Siti Aisyah} and {Abu Bakar}, {Mohd Aftar} and {Mohd Ariff}, Noratiqah",
year = "2018",
month = "1",
day = "1",
doi = "10.1080/03610926.2018.1535073",
language = "English",
journal = "Communications in Statistics - Theory and Methods",
issn = "0361-0926",
publisher = "Taylor and Francis Ltd.",

}

TY - JOUR

T1 - Volatility forecasting of financial time series using wavelet based exponential generalized autoregressive conditional heteroscedasticity model

AU - Mohammed, Siti Aisyah

AU - Abu Bakar, Mohd Aftar

AU - Mohd Ariff, Noratiqah

PY - 2018/1/1

Y1 - 2018/1/1

N2 - An improved forecasting model by merging two different computational models in predicting future volatility was proposed. The model integrates wavelet and EGARCH model where the pre-processing activity based on wavelet transform is performed with de-noising technique to eliminate noise in observed signal. The denoised signal is then feed into EGARCH model to forecast the volatility. The predictive capability of the proposed model is compared with the existing EGARCH model. The results show that the hybrid model has increased the accuracy of forecasting future volatility.

AB - An improved forecasting model by merging two different computational models in predicting future volatility was proposed. The model integrates wavelet and EGARCH model where the pre-processing activity based on wavelet transform is performed with de-noising technique to eliminate noise in observed signal. The denoised signal is then feed into EGARCH model to forecast the volatility. The predictive capability of the proposed model is compared with the existing EGARCH model. The results show that the hybrid model has increased the accuracy of forecasting future volatility.

KW - de-noising

KW - EGARCH model

KW - volatility

KW - Wavelet transform

UR - http://www.scopus.com/inward/record.url?scp=85059009842&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059009842&partnerID=8YFLogxK

U2 - 10.1080/03610926.2018.1535073

DO - 10.1080/03610926.2018.1535073

M3 - Article

JO - Communications in Statistics - Theory and Methods

JF - Communications in Statistics - Theory and Methods

SN - 0361-0926

ER -