We re-examine diversification benefits of investing in commodities and currencies by considering a risk-averse investor with mean-variance preferences who exploits the possibility of predictable time variation in asset return means, variances, and covariances. We implement unconditional and...

We examine machine learning and factor-based portfolio optimization. We find that factors based on autoencoder neural networks exhibit a weaker relationship with commonly used characteristic-sorted portfolios than popular dimensionality reduction techniques. Machine learning methods also lead to...

We find out-of-sample predictability of commodity futures excess returns using combination forecasts of 28 potential predictors. Such gains in forecast accuracy translate into economically significant improvements in certainty equivalent returns and Sharpe ratios for a mean-variance investor....