This paper shows that investments based on deep learning signals extract profitability from
difficult-to-arbitrage stocks and during high limits-to-arbitrage market states. In particular …

We investigate how transaction costs change the number of characteristics that are jointly
significant for an investor's optimal portfolio and, hence, how they change the dimension of …

This study seeks to inform investment academics and practitioners by describing and
analyzing the population of return predictive signals (RPS) publicly identified over the 40 …

We zero in on the expected returns of long-short portfolios based on 204 stock market
anomalies by accounting for i) effective bid–ask spreads, ii) post-publication effects, and iii) …

Deep learning is an active area of research in machine learning. I train deep feedforward
neural networks (DFN) based on a set of 68 firm characteristics (FC) to predict the US cross …

Aiming to optimally harvest global equity factor premiums, we investigated the benefits of
parametric portfolio policies for timing factors conditioned on time-series predictors and …

Hundreds of variables have been proposed to predict the cross-section of stock returns; see,
for instance, Harvey, Liu, and Zhu (2015), McLean and Pontiff (2016), and Hou, Xue, and …

We study the post-publication trading costs of 120 stock market anomalies. Trading costs
use effective bid-ask spreads from high-frequency ISSM and TAQ data when available and …

We show that the introduction of a leverage constraint improves the practical implementation
of characteristics-based portfolios. The addition of the constraint leads to significantly lower …

The distribution of long-run compound returns to portfolio strategies is greatly affected by
periodic rebalancing. Over time, buy-and-hold portfolios gradually lose diversification as …