It is well known that estimated mean-variance portfolios deliver, on average, poor out-of-sample performance. A lesser-known fact that we characterize in this paper is that their out-of-sample performance is also very volatile. Using our analytical characterization of out-of-sample performance...

This study presents an improvement to the mean-variance portfolio optimization model, by considering both the integer transaction lots and a robust estimator of the covariance matrices. Four robust estimators were tested, namely the Minimum Covariance Determinant, the S, the MM, and the...

We propose a new dimension reduction procedure for portfolio optimization. The vanilla principal component analysis (PCA) restricts the portfolio on the linear subspace spanned by the PCs, which often requires many PCs to performance well. In our framework, the linear subspace is based on a most...