An Empirical Study on the Modeling of an Optimal Investment Portfolio Using Multivariate Model of Conditional Heteroscedasticity: Evidence from the Chinese Stock Exchanges

DOI

10.2991/aebmr.k.200312.179How to use a DOI?

Abstract

For any subject of economic relations, the main purpose of investments is to maximize income and minimize risks, as well as to save money from inflation. The best way to achieve this goal is a portfolio approach to investment. Nowadays, there are plenty of strategies and techniques for the construction and management of the investment portfolio, therefore, the problem of choosing the most effective investment policy is particularly relevant for any investor. Markowitz portfolio optimization model is very popular among investors around the world in recent decades, but also is criticized a lot by different scholars. To mitigate the problems of the Markowitz optimization model, we decided to apply multivariate time series forecast to an optimization process and examined, whether the use of multivariate time series models in a portfolio optimization process can improve portfolio performance and decrease overall volatility. Using a Markowitz optimization model and the BEKK GARCH model, portfolios for different levels of risk has been constructed for the Shanghai Stock Exchange and Hong Kong Stock Exchange. Backtesting results show, that in fact, portfolios constructed through a multivariate time series forecast decrease overall portfolio volatility. Also, we have found, that applied models outperformed the stock market indexes, which confirms the efficiency of the implementation of both models for portfolio construction techniques.

Copyright

© 2020, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - A Shchankina
AU  - Zou Ping
PY  - 2020
DA  - 2020/03/17
TI  - An Empirical Study on the Modeling of an Optimal Investment Portfolio Using Multivariate Model of Conditional Heteroscedasticity: Evidence from the Chinese Stock Exchanges
BT  - Proceedings of the International Scientific Conference "Far East Con" (ISCFEC 2020)
PB  - Atlantis Press
SP  - 1300
EP  - 1311
SN  - 2352-5428
UR  - https://doi.org/10.2991/aebmr.k.200312.179
DO  - 10.2991/aebmr.k.200312.179
ID  - Shchankina2020
ER  -