This paper describes a process for automatically generating academic finance papers using large language models (LLMs). It demonstrates the process' efficacy by producing hundreds of complete papers on stock return predictability, a topic particularly well-suited for our illustration. We first...

We examine how investor sentiment affects the cross-section of stock returns. Theory predicts that a broad wave of sentiment will disproportionately affect stocks whose valuations are highly subjective and are difficult to arbitrage. We test this prediction by studying how the cross-section of...

Using a longer time period and both NYSE-Amex and Nasdaq stocks, this paper examines short interest and stock returns in more detail than any previous study and finds that many documented patterns are not robust. While equally weighted high short interest portfolios generally underperform, value...

Motivated by the observation that survey expectations of stock returns are inconsistent with rational return expectations under real-world probabilities, we investigate whether alternative expectations hypotheses entertained in the asset pricing literature are consistent with the survey...

We perform a comparative analysis of machine learning methods for the canonical problem of empirical asset pricing: measuring asset risk premia. We demonstrate large economic gains to investors using machine learning forecasts, in some cases doubling the performance of leading regression-based...

We study the transmission of sovereign debt inflow shocks on domestic firms. We exploit episodes of large sovereign debt inflows in six emerging countries that are due to the announcements of these countries' inclusion in two major local-currency sovereign debt indexes. We show that these...

Firm-level stock returns differ enormously in reaction to COVID-19 news. We characterize these reactions using the Risk Factors discussions in pre-pandemic 10-K filings and two text-analytic approaches: expert-curated dictionaries and supervised machine learning (ML). Bad COVID-19 news lowers...

We construct a slope factor from changes in federal funds futures of different horizons. Slope predicts stock returns at the weekly frequency: faster monetary policy easing positively predicts excess returns. Investors can achieve increases in weekly Sharpe ratios of 20% conditioning on the...

We provide a systematic analysis of the properties of individual returns to wealth using twenty years of population data from Norway's administrative tax records. We document a number of novel results. First, in a given cross-section, individuals earn markedly different returns on their assets,...

This paper analyzes a novel data set of commodity futures prices over a long sample period starting in 1877, which allows us to shed new light on several important and controversial questions. We document that commodity futures returns (1) have been positive on average; (2) vary significantly...