An earnings manipulation detection model based on forensic accounting principles (Beneish 1999) has substantial out-of-sample ability to predict cross-sectional returns. We show that the model correctly identified, ahead of time, 12 of the 17 highest profile fraud cases in the period 1998-2002....

An accounting-based earnings manipulation detection model has strong out-of-sample power to predict cross-sectional returns. Companies with a higher probability of manipulation (M-score) earn lower returns on every decile portfolio sorted by size, book-to-market, momentum, accruals, and short...

We introduce a new approach to predicting market returns using the cross-section of earnings and book values to explain current stock prices and extract aggregate expected returns. The proposed measure is countercyclical; it portends a significant fraction of the time-series variation in stock...