上市公司的财务舞弊会对股东以及市场造成难以预计的伤害。为了及时发现和防止财务舞弊，需要有效的检测手段。在对舞弊特征指标研究相关文献回顾的基础上，本研究构建了两套指标体系——12 项财务比率与 28 项原始财务数据项。本研究使用了一种集成学习方法 XGBoost 作为分类器，开发了一个新型的财务舞弊识别模型。为了评估模型的性能，以 AUC 作为性能评价指标，并与两个基准模型——基于财务比率的 Logistic 回归模型和基于原始数据项的 Adaboost 模型作对比。结果表明，本研究新构建的模型性能超过了两个基准模型。

Accounting fraud, usually difficult to detect, can cause significant harm to stakeholders and serious damage to the market. Effective methods of accounting fraud detection are needed for the prevention and governance of accounting fraud. In this study, we construct two sets of indicator systems-12 financial ratios and 28 raw financial data items. And we develop a novel accounting fraud prediction model using XGBoost, a powerful ensemble learning approach. To assess the performance of fraud prediction models, we select AUC as evaluation metric and two benchmark models - Logistic Regression model and Adaboost model. Results show that: our XGBoost-based prediction model outperforms two benchmark models by a large margin whatever model inputs.