Financial Fraud Detection of Listed Companies in China: A Machine Learning Approach

As the focus of capital market supervision, financial report fraud has shown a development trend enormous numbers, complex transactions, and hidden means in recent years. To improve audit efficiency reduce dependence on non-financial data, study only uses structured original data to constructs new identification model, which can quickly detect China. This takes listed companies China from 1998 2016 as research samples selects 28 sets raw reports. Then, this compares detection effectiveness two single classification machine learning algorithms five ensemble detection. Compared with algorithms, results show that are generally better at detecting for Chinese companies, stacking algorithm performs best. The provide direct evidence rapid using algorithms. first proposes algorithm-based reporting model China, provides simple effective approach investors, regulators, management. It also reference other scenarios.