Neural Network Copula Portfolio Optimization for Exchange Traded Funds

Quantitative Finance, forthcoming

26 Pages Posted: 1 Dec 2016 Last revised: 5 Jan 2018

See all articles by Yang Zhao

Yang Zhao

Central University of Finance and Economics (CUFE) - Chinese Academy of Finance and Development

Charalampos Stasinakis

University of Glasgow, Department of Economics

Georgios Sermpinis

University of Glasgow

Yukun Shi

University of Glasgow

Date Written: November 15, 2017

Abstract

This paper attempts to investigate if adopting accurate forecasts from Neural Network (NN) models can lead to statistical and economically significant benefits in portfolio management decisions. In order to achieve that, three NNs, namely the Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN) and the Psi Sigma Network (PSN), are applied to the task of forecasting the daily returns of three Exchange Traded Funds (ETFs). The statistical and trading performance of the NNs is benchmarked with the traditional Auto-Regressive Moving Average (ARMA) models. Next, a novel dynamic asymmetric copula model (NNC) is introduced in order to capture the dependence structure across ETF returns. Based on the above, weekly re-balanced portfolios are obtained and compared by using the traditional mean-variance and the mean-CVaR portfolio optimization approach. In terms of the results, PSN outperforms all models in statistical and trading terms. Additionally, the asymmetric skewed t copula statistically outperforms symmetric copulas when it comes to modelling ETF returns dependence. The proposed NNC model leads to significant improvements in the portfolio optimization process, while forecasting covariance accounting for asymmetric dependence between the ETFs also improves the performance of obtained portfolios.

Keywords: Copulas, Neural Networks, Portfolio Optimization, ETF

JEL Classification: G11, G17

Suggested Citation

Zhao, Yang and Stasinakis, Charalampos and Sermpinis, Georgios and Shi, Yukun, Neural Network Copula Portfolio Optimization for Exchange Traded Funds (November 15, 2017). Quantitative Finance, forthcoming, Available at SSRN: https://ssrn.com/abstract=2877966 or http://dx.doi.org/10.2139/ssrn.2877966

Yang Zhao

Central University of Finance and Economics (CUFE) - Chinese Academy of Finance and Development ( email )

39 South College Road
Beijing
China

Charalampos Stasinakis

University of Glasgow, Department of Economics ( email )

Adam Smith Business School
Glasgow, Scotland G12 8LE
United Kingdom

Georgios Sermpinis

University of Glasgow ( email )

Adam Smith Business School
Glasgow, Scotland G12 8LE
United Kingdom

Yukun Shi (Contact Author)

University of Glasgow ( email )

Adam Smith Business School
Glasgow, Scotland G12 8LE
United Kingdom

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
446
Abstract Views
1,664
Rank
119,180
PlumX Metrics