Yukun Shi

Neural Network Copula Portfolio Optimization for Exchange Traded Funds

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, Recurrent Neural Network 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 Autoregressive Moving Average 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 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.

Does the Introduction of Index Futures Stabilize Stock Markets? Further Evidence from Emerging Markets

We examine how the introduction of index futures affects the stability of stock markets in seven emerging countries (Brazil, Russia, India, China, and South Africa [BRICS] and two countries in Europe, i.e. Poland and Turkey) by studying the existence and the impact of positive feedback trading in both pre- and post-futures periods, using augmented Sentana and Wadhwani’s (1992) feedback model. Consistent with evidence in mature markets before the introduction of index futures, positive feedback traders are already prevalent in six out of the seven markets studied. After the introduction of index futures, signs of positive feedback trading have emerged in only three markets (Poland, South Africa, and Turkey). In contrast to evidence in developed markets, positive feedback traders migrate from spot to futures markets in only three markets (India, Russia, Poland), which suggests that the introduction of index futures may destabilize some emerging stock markets. Another interesting finding is that positive feedback trading is more intense in the majority of the markets (Brazil, China, Russia, and Turkey) during market declines. Overall, the impact of the introduction of index futures on the stability of emerging stock markets is not only different from that of mature markets but also differs among individual emerging markets. We discuss the policy implications of the findings.

Market Efficiency, Information Flows and Hedging Performance in Carbon Markets

In this study, we examine the market efficiency of both the European and the U.S. carbon markets. Athreshold vector error correction model (TVECM) is adopted, which makes our paper the first to allow for the threshold effect and asymmetric price adjustments in market efficiency analysis. The results indicate that the market efficiency is strongly violated in both the European and the U.S. carbon markets in the short term. This generates the interest to examine information flows between the European and the U.S. market, and the results from a bivariate AR-GARCH model indicate that there is evidence for volatility spillover between the two markets. Finally, we examine the performance of several hedging strategies in carbon markets. We find that the European carbon futures market cannot provide effective risk management function to carbon market participants due to its market inefficiency in the long run, while the U.S. carbon market provides much better hedging performance due to its long term market efficiency.