Aumentar Tamaño del texto Disminuir Tamaño del texto

André Santos, Universidad Carlos III de Madrid, Universidade Federal de Santa


Semiparametric Portfolio Policies


We develop a semiparametric portfolio optimization method in which portfolio weights are parameterized as a nonlinear function of firm characteristics. This approach generalizes the traditional linear parametric portfolio policy of Brandt et al (2009) and can be applied to high-dimensional problems involving hundreds or thousands of assets at a relatively  low computational cost. An empirical implementation exploiting the size, value, and momentum anomalies in the universe of CRSP stocks confirms that nonlinearities factors are important for portfolio construction. Moreover, an out-of-sample evaluation  indicates that the semiparametric policy outperforms the traditional parametric policy as well as the equally- and value-weighted strategies in terms of returns, risk, and risk-adjusted returns both in the absence and  in the presence of transaction costs. Our evidence suggests that allowing for a more flexible relation between portfolio weights and firm characteristics can provide a more accurate description of the empirical patterns seen in data.