Machine Learning Portfolios with Equal Risk Contributions
30 Pages Posted: 8 Aug 2019 Last revised: 1 Sep 2019
Date Written: August 6, 2019
We use machine learning methods to forecast individual stock returns and create long-short portfolios in the Brazilian stock market, using a rich data set including technical and fundamental predictive signals. We further develop an algorithm that combines long-short portfolios obtained with various machine learning methods such that (i) the risk contributions of all individual long-short portfolios are equal, and (ii) the aggregate risk contribution of all long positions equals that of all short positions. Compared with an equally-weighted combination of the original portfolios, the portfolio obtained with our algorithm has over twice the Sharpe ratio and less than a third of the maximum drawdown.
Keywords: machine learning, forecasting, return prediction, risk parity, equal risk contribution
JEL Classification: C53, G11, G15
Suggested Citation: Suggested Citation