We use machine learning methods and high-dimensional detailed financial data to predict the direction of one-year-ahead earnings changes. Our models show significant out-of-sample predictive power: the area under the receiver operating characteristics curve ranges from 67.52% to 68.66%,...

There is relatively little prior evidence on the potential impact of rank and file employees on financial reporting choices outside union negotiations. We contribute to the literature by providing new evidence that firms appear to manage long-run earnings upward in order to manage employee...