Fusing Economic Indicators for Portfolio Optimization - A Simulation-Based Approach

Abstract

Portfolio optimization and quantitative risk management have been extensively studied since the 1990s, and attracted even more attention after the financial crisis in 2008. Such a disastrous event required portfolio managers to better manage the risk and return trade-off when building their clients' portfolios. With that said, the advancement of machine-learning algorithms and computing resources helps portfolio managers explore rich information by incorporating the macro-economy conditions into their investment strategies and optimizing their portfolio performance in a timely manner. In this paper, we present a simulation-based approach by fusing eleven macroeconomic factors using Neural Networks (NN) to build an Economic Factor-based Predictive Model (EFPM). Then, we combine it with Copula-GARCH simulation model and the Mean-Conditional Value at Risk (Mean-CVaR) framework to derive an optimal portfolio comprised of six index funds. Empirical test on the achieved portfolio is conducted on an out-of-sample dataset utilizing a rolling-horizon approach. Finally, we compare its performance against the three benchmark portfolios over a twelve-year period (01/2007 - 12/2018). The results indicate that the proposed EFPM-based asset allocation strategy outperforms the three alternatives on many common metrics, including annualized return, 99% VaR, and Sharpe ratio.