Mean-variance analysis

  • 详情 When Markowitz Meets Machine: Optimization of Large Portfolios with High-Dimensional Stock Characteristics
    We propose a novel portfolio optimization framework that transforms the classic Markowitz mean-variance optimization into an unconstrained machine learning task. Our approach, Markowitz Meets Machine (MMM), directly utilizes high-dimensional firm characteristics as inputs to generate portfolio weights, without requiring explicit estimation of expected returns or covariance matrix. The MMM model balances the mean-variance tradeoff but circumvents many implementation challenges of traditional mean-variance optimization (MVO). Using China A-share market data with 267 proprietary signals, we construct long-only optimal portfolios that target outperformance relative to the CSI 300 and CSI 500 benchmarks. The MMM portfolio outperforms the CSI 500 benchmark by approximately 20% annually with tracking errors around 5%, significantly exceeding the performance of traditional multi-step MVO approaches after accounting for transaction costs. Our results demonstrate the importance of integrated modeling of expected returns, risk, and optimization.
  • 详情 An Analysis of Portfolio Selection with Background Risk
    This paper investigates the impact of background risk on an investor’s portfolio choice in a mean–variance framework, and analyzes the properties of efficient portfolios as well as the investor’s hedging behavior in the presence of background risk. Our model implies that the efficient portfolio with background risk can be separated into two independent components: the traditional mean–variance efficient portfolio and a self-financing component constructed to hedge against background risk. Our analysis also shows that the presence of background risk shifts the efficient frontier of financial assets to the right with no changes in its shape. Moreover, both the composition of the hedge portfolio and the location of the efficient frontier are greatly affected by a number of background risk factors, including the proportion of background assets in total wealth and the correlation between background risk and financial risk.
  • 详情 An Analysis of Portfolio Selection with Background Risk
    This paper investigates the impacts of background risk on investors’ portfolio choice in a mean-variance framework and analyzes the properties of the selected portfolio and investors’ hedging behaviour. Our model implies that the optimal portfolio with background risk can be separated into two independent components: the traditional mean-variance optimal portfolio and the self-financing portfolio constructed to hedge against background risk. Our results show that both the composition and risk of the optimal portfolio are greatly affected by a number of background risk factors, including the quantity and risk of the assets that are exposed to background risk, as well as the correlation between background assets and those in the portfolio.
0.153660s