A0816
Title: Nonparametric portfolio choices with firm characteristics
Authors: Rohan Sen - USI Lugano (Switzerland) [presenting]
Abstract: The aim is to present a novel approach to constructing optimal mean-variance portfolio rules, particularly when the number of assets is proportional to the number of samples. The approach models the portfolio weight of each asset as a nonparametric nonlinear function of firm-level characteristics and utilizes an equivalent unconstrained regularized formulation of the original mean-variance optimization problem. The framework generalizes to minimum-variance portfolios with short-sale constraints. The resulting portfolio rule is straightforward to implement, computationally efficient, and flexible.
