Machine Learning Classification and Portfolio Allocation: with Implications from Machine Uncertainty
This work addresses portfolio allocation for investors by identifying outperforming and underperforming stocks, though it is incremental as it builds on existing machine learning methods in finance.
The paper tackles stock performance prediction using multi-class machine learning classifiers, achieving annual Sharpe ratios of 1.67 to 3.35 and alphas of 29% to 48% in long-short portfolios, with results robust after controlling for regressions and in large-cap stocks.
We use multi-class machine learning classifiers to identify the stocks that outperform or underperform other stocks. The resulting long-short portfolios achieve annual Sharpe ratios of 1.67 (value-weighted) and 3.35 (equal-weighted), with annual alphas ranging from 29\% to 48\%. These results persist after controlling for machine learning regressions and remain robust among large-cap stocks. Machine uncertainty, as measured by predicted probabilities, impairs the prediction performance. Stocks with higher machine uncertainty experience lower returns, particularly when human proxies of information uncertainty align with machine uncertainty. Consistent with the literature, such an effect is driven by the past underperformers.