Machine learning portfolios with equal risk contributions: evidence from the Brazilian market

Abstract

We investigate the use of machine learning (ML) to forecast stock returns in the Brazilian market usinga rich proprietary dataset. While ML portfolios can easily outperform the local market, the performanceof long-short strategies using ML is hampered by the high volatility of the short portfolios. We showthat an Equal Risk Contribution (ERC) approach significantly improves risk-adjusted returns. We furtherdevelop an ERC approach that combines multiple long-short strategies obtained with ML models, equal-izing risk contributions across ML models, which outperforms, on a risk-adjusted basis, all individualML long-short strategies, as well as alternative combinations of ML strategies.

Keywords: emerging markets, machine learning, stock market prediction, portfolio optimization, equalrisk contribution, risk parity

JEL Classification: C53, G11, G15