We analyze early-venture fundraising from dispersed, endogenously informed investors. An entrepreneur chooses a payoff-maximizing offering, and investors communicate their information by either contributing capital or abstaining. The entrepreneur uses the information conveyed by fundraising amounts to decide whether or not to undertake a risky venture. His decision threshold hedges investors against bad projects, creating a “loser’s blessing” that encourages contributing without information. Making the offering less attractive to investors mitigates the loser’s blessing but can give rise to a winner’s curse. Both tensions reduce financing efficiency.

We use a machine learning technique to assess whether the thematic content of financial statement disclosures (labeled topic ) is incrementally informative in predicting intentional misreporting. Using a Bayesian topic modeling algorithm, we determine and empirically quantify the topic content of a large collection of 10‐K narratives spanning 1994 to 2012. We find that the algorithm produces a valid set of semantically meaningful topics that predict financial misreporting, based on samples of Securities and Exchange Commission (SEC) enforcement actions (Accounting and Auditing Enforcement Releases [AAERs]) and irregularities identified from financial restatements and 10‐K filing amendments. Our out‐of‐sample tests indicate that topic significantly improves the detection of financial misreporting by as much as 59% when added to models based on commonly used financial and textual style variables. Furthermore, models that incorporate topic significantly outperform traditional models when detecting serious revenue recognition and core expense errors. Taken together, our results suggest that the topics discussed in annual report filings and the attention devoted to each topic are useful signals in detecting financial misreporting.