Data-driven optimization in management.

Highlights from the article: They are ordered within the cluster considering first two contributions relying on static optimization methods, the first of which by Torri et al. with a relevant methodological content and the second by Giuzio and Paterlini addressing directly the implications of high market correlations for portfolio managers, and then the article by Barro et al. employing a dynamic optimization approach again in the presence of alternative volatility regimes. The article on Sparse Precision Matrices for Minimum Variance Portfolios by Torri, Giacometti and Paterlini focuses on regularization methods used in the estimation of the precision matrix, an essential input in mean-variance optimization and here considered for minimum variance portfolios. Giuzio and Paterlini show that constraining the sparse lq-norm of portfolio weights automatically controls diversification and selects portfolios with a small number of active weights and low risk, in presence of high correlation and volatility.