High-Throughput Asset Pricing

TL;DR

This paper introduces a high-throughput empirical Bayes approach to evaluate a vast array of asset pricing strategies, achieving top journal performance while avoiding look-ahead bias and providing unbiased, interpretable predictions.

Contribution

It develops a novel high-throughput empirical Bayes methodology for unbiased asset pricing analysis, outperforming traditional multiple testing methods and offering transparent insights.

Findings

Empirical Bayes matches top journal performance in out-of-sample testing.

Predictability is concentrated in accounting strategies, small stocks, and pre-2004 periods.

Traditional multiple testing methods fail to identify most out-of-sample performers.

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.