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...

This paper contributes to the ongoing debate of whether active investing is still worthwhile in presence of factor investing. It provides a universal framework that selects presumably factor-heavy fixed-income funds. To test the framework, returns of an exemplary fund are neutralized for factor...