A New Variable in Corporate Disclosure Analysis : An AI Study of the SEC EDGAR Database

Corporate disclosures have been studied for many years. We add a new dimension to the analysis: we show that the filing frequency of disclosures has a negative impact on future stock returns. Specifically, we show that every additional filing within the past month preceding a given filing reduces the average expected return by nearly 0.20% over the two weeks post-filing. The frequency of filings is just one of several significant drivers we identify using a latent factor identification model by Aldridge and Guan (2021). This Artificial Intelligence (AI) methodology and other factors it discovers can be useful to investors looking to quickly and efficiently process filings, as well as corporations looking to optimize their filings and the regulators looking to parse for filing issues