We integrate fundamental analysis with mean-variance portfolio optimization by using a fundamentals-based model to estimate expected returns and a state-of-the-art nonlinear shrinkage estimator to estimate the covariance matrix of individual stock returns to form mean-variance optimized portfolios. We find that these optimized fundamental portfolios yield substantial improvements in portfolio performance relative to equal-weighted and value-weighted portfolios of stocks in the extreme decile of expected returns, an approach commonly used in fundamental analysis research, and relative to both factor-based and parametric portfolio policy approaches used in the prior literature. The optimized fundamental portfolios produce large outof-sample factor alphas with high Sharpe ratios. The relative performance gains are persistent through time, remain when small capitalization firms are eliminated from the investment set, and are robust to incorporating estimated transactions costs. Future fundamental analysis research could perhaps provide greater investment insights by implementing this portfolio optimization approach.
Fonte: Lyle, Matthew, and Teri L. Yohn. 2020. Fundamental Analysis and Optimal Portfolio Construction.
Nenhum comentário:
Postar um comentário