Does Peer-Reviewed Research Help Predict Stock Returns?
Study compares peer-reviewed research and data mining in predicting stock returns, finding similar post-sample performance.
What it examines
The paper investigates whether peer-reviewed research helps predict stock returns compared to naive data mining. It constructs empirical counterparts by matching 200 published predictors to data-mined benchmarks from 29,000 accounting ratios, examining post-sample returns to assess predictability.
What it concludes
The research implies that data mining is undervalued in asset pricing, as it can uncover substantial out-of-sample returns. Future research should explore integrating data mining with economic theories to enhance predictability. Potential applications include improving investment strategies and financial modeling.
Evidence objects
The research implies that data mining is undervalued in asset pricing, as it can uncover substantial out-of-sample returns. Future research should explore integrating data mining with economic theories to enhance predictability. Potential applications include improving investment strategies and financial modeling.
key_findings bullet 1 · key_findings · validation V0
Raw abstract and provenance
Abstract: Mining 29,000 accounting ratios for t-statistics over 2.0 leads to cross-sectional return predictability similar to the peer review process. For both methods, about 50% of predictability remains after the original sample periods. Predictors supported by peer-reviewed risk explanations or equilibrium models underperform other predictors post-sample, suggesting peer review systematically mislabels m… ▽ More Mining 29,000 accounting ratios for t-statistics over 2.0 leads to cross-sectional return predictability similar to the peer review process. For both methods, about 50% of predictability remains after the original sample periods. Predictors supported by peer-reviewed risk explanations or equilibrium models underperform other predictors post-sample, suggesting peer review systematically mislabels mispricing as risk, though only 20% of predictors are labelled as risk. Data mining generates other features of peer review including the rise in returns as original sample periods end and the speed of post-sample decay. It also uncovers themes like investment, issuance, and accruals -- decades before they are published. △ Less
Source row: 639 · abstract type: unknown