Detecting Accounting Fraud in Publicly Traded U.S. Firms Using a Machine Learning Approach

TLDR

The authors aim to build a fraud prediction model for publicly traded U.S. firms by integrating domain knowledge with machine learning techniques. They construct the model using theory‑motivated raw accounting figures, apply ensemble learning rather than logistic regression, and evaluate it with a ranking‑based metric tailored to fraud detection.

Abstract

ABSTRACT We develop a state‐of‐the‐art fraud prediction model using a machine learning approach. We demonstrate the value of combining domain knowledge and machine learning methods in model building. We select our model input based on existing accounting theories, but we differ from prior accounting research by using raw accounting numbers rather than financial ratios. We employ one of the most powerful machine learning methods, ensemble learning, rather than the commonly used method of logistic regression. To assess the performance of fraud prediction models, we introduce a new performance evaluation metric commonly used in ranking problems that is more appropriate for the fraud prediction task. Starting with an identical set of theory‐motivated raw accounting numbers, we show that our new fraud prediction model outperforms two benchmark models by a large margin: the Dechow et al. logistic regression model based on financial ratios, and the Cecchini et al. support‐vector‐machine model with a financial kernel that maps raw accounting numbers into a broader set of ratios.