Journal
JOURNAL OF ACCOUNTING RESEARCH
Volume 58, Issue 1, Pages 199-235Publisher
WILEY
DOI: 10.1111/1475-679X.12292
Keywords
C53; M41; fraud prediction; machine learning; ensemble learning
Categories
Funding
- Singapore Ministry of Education Tier 2 grant [MOE2012-T2-1-045]
- NSFC [71601116]
- Shanghai Pujiang Program [16PJC045]
- MOE start-up grant [R-521-000-032-133]
- National Natural Science Foundation of China [71971164, 91646206]
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available