Recently many research articles have focused on the prediction of stock returns using machine learning methods. All show that regression trees and neural networks have superior predicting power than linear models. In this paper we analyze the performance of investable portfolios built using...

We analyze the performance of investable portfolios built using predicted stock returns from machine learning methods and attribute their performance to linear, marginal non-linear and interaction effects. We use a large set of features including price-based, fundamental-based, and...

Present market instabilities have prompted great interest on the characteristics of specific portfolios such as minimum variance and equally- weighted risk contribution portfolios as these portfolios do not rely on the estimate of expected returns. Indeed, in turmoil periods traditional market...