Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/192053
Title: AN ENSEMBLE OF MACHINE LEARNING AND ECONOMETRICS VOLATILITY FORECASTING METHODS
Authors: TUAN DING WEI
Keywords: Volatility Forecasting
Statistical Machine Learning
Ensemble Learning
Issue Date: 5-Apr-2021
Citation: TUAN DING WEI (2021-04-05). AN ENSEMBLE OF MACHINE LEARNING AND ECONOMETRICS VOLATILITY FORECASTING METHODS. ScholarBank@NUS Repository.
Abstract: The existing evidence on the effectiveness of machine learning hybrid models in forecasting volatility remains mixed. This paper examines the use of Support Vector Machine (SVM) and Artificial Neural Network (ANN) to estimate the parameters of Generalised Autoregressive Conditional Heteroskedasticity (GARCH) models in a currency and an equity dataset. We found evidence that SVM-GARCH only works under certain circumstances while ANN-GARCH was largely ineffective. Nevertheless, using ensemble learning, also known as forecast combination, we were able to achieve performance improvements where both Heterogeneous Autoregressive-Realized Volatility (HAR-RV) and GARCH based models, as well as both econometrics and machine learning models were used in the combinations of forecast. It should be recognised that there is no one-size-fit all model for different asset classes and for all timeframes. It is therefore necessary to combine forecasts and leverage on the strengths of each model.
URI: https://scholarbank.nus.edu.sg/handle/10635/192053
Appears in Collections:Bachelor's Theses

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
Tuan Ding Wei AY2021 Sem 2.pdf958.19 kBAdobe PDF

RESTRICTED

NoneLog In

Page view(s)

34
checked on Jul 29, 2021

Download(s)

15
checked on Jul 29, 2021

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.