Abstract: We develop a novel methodology for constructing forecast confidence intervals (FCI) for stock return predictions obtained from machine learning (ML) models. We show that the FCI for forecasts from sophisticated ML methods, which are difficult to assess directly, asymptotically aligns with the FCI of forecasts obtained using simpler nonparametric methods. Therefore, the FCI for deep neural network models can be effectively approximated by that of simpler B-spline models using standard methods. Utilizing these FCIs, we address optimal portfolio choice problems for an uncertainty-averse (UA) investor with a mean-variance utility function. We establish a "no-holding" position, where the UA investor refrains from investing in risky assets if the uncertainty exceeds a certain threshold.
Abstract: We apply empirical Bayes (EB) to mine data on 136,000 long-short strategies constructed from accounting ratios, past returns, and ticker symbols. This ``high-throughput asset pricing'' matches the out-of-sample performance of top journals while eliminating look-ahead bias. Naively mining for the largest Sharpe ratios leads to similar performance, consistent with our theoretical results, though EB uniquely provides unbiased predictions with transparent intuition. Predictability is concentrated in accounting strategies, small stocks, and pre-2004 periods, consistent with limited attention theories. Multiple testing methods popular in finance fail to identify most out-of-sample performers. High-throughput methods provide a rigorous, unbiased framework for understanding asset prices.
Discussant: Alessio Sasaretto, Federal Reserve Bank of Dallas
Abstract: We propose a statistical model of heterogeneous beliefs where investors are represented as different machine learning model specifications. Investors form return forecasts from their individual models using common data inputs. We measure disagreement as forecast dispersion across investor-models (MFD). Our measure aligns with analyst forecast disagreement but more powerfully predicts returns. We document a large and robust association between belief disagreement and future returns. A decile spread portfolio that sells stocks with high disagreement and buys stocks with low disagreement earns a value-weighted return of 14% per year. Further analyses suggest MFD-alpha is mispricing induced by short-sale costs and limits-to-arbitrage.
Discussant: Ali Kakhbod, University of California-Berkeley
