Financial Fraud Recognition Method for Listed Companies Based on Deep Learning and Textual Emotion

doi:10.3778/j.issn.1002-8331.2305-0281

Abstract

Abstract: Financial fraud of listed companies refers to the untrustworthy behavior of distorting accounting information by improper means, which has a negative impact on company operations, economic development, and social interests. At present, more research focuses on financial digital data, and less research on text information and deep learning algorithms. Therefore, a financial fraud recognition method for listed companies based on deep learning and textual emotional feature is proposed. Firstly, the method selects and preprocesses the financial indicators, and uses Bi-LSTM to extract the emotional features of the stock review text. Then, the method uses the RCC (residual-cross-convolutional) parallel network to recognize financial fraud. The network uses residual network, cross network, convolutional network and long short-term memory network to extract financial fraud features in parallel, and uses batch normalization and full connection to obtain the final recognition result. The experiment results show that this method achieves better results than other models in recognizing financial fraud for listed companies, with a recall rate and AUC of 88.46% and 82.06% respectively.

Key words: financial fraud, textual emotional feature, deep learning, residual network, cross network

摘要： 上市公司财务舞弊是指采用不当手段使会计信息失真的恶劣失信行为，对公司经营、经济发展和社会利益产生负面影响。目前，更多研究关注于金融数字数据，对文本信息和深度学习算法的研究较少，因此提出了一种基于深度学习并融合文本情感特征的上市公司财务舞弊识别方法。该方法首先对财务指标进行预处理，并使用Bi-LSTM提取股评文本的情感特征。然后使用RCC（residual-cross-convolutional）并行网络进行财务舞弊识别，其采取残差网络、交叉网络、卷积网络和长短期记忆网络并行的方式提取财务舞弊特征，并使用批标准化和全连接得到最终的识别结果。实验结果表明，该方法在识别上市公司财务舞弊的任务上较其他模型取得了更好的效果，召回率和AUC分别达到了88.46%和82.06%。

关键词: 财务舞弊, 文本情感特征, 深度学习, 残差网络, 交叉网络

CAO Ce, CHEN Yan, ZHOU Lanjiang. Financial Fraud Recognition Method for Listed Companies Based on Deep Learning and Textual Emotion[J]. Computer Engineering and Applications, 2024, 60(4): 338-346.

曹策, 陈焰, 周兰江. 基于深度学习和文本情感的上市公司财务舞弊识别方法[J]. 计算机工程与应用, 2024, 60(4): 338-346.

References

[1] 高晶. 财务报表欺诈与舞弊的手段、危害及治理研究[J]. 商业会计, 2019(24): 85-87.
GAO J. Financial statement fraud and fraud means, harm and governance research[J]. Commercial Accounting, 2019(24): 85-87.
[2] 张秋三, 张磊, 张宁, 等. 基于数据挖掘的上市公司财务舞弊识别研究[J]. 科技和产业, 2014, 14(11): 77-80.
ZHANG Q S, ZHANG L, ZHANG N, et al. Research on the financial fraud identification of the listed companies based on data mining techniques[J]. Science Technology and Industry, 2014, 14(11): 77-80.
[3] 许文杰. 上市公司财务舞弊行为识别研究[D]. 杭州: 浙江大学, 2022.
XU W J. Research on identification of financial fraud of listed companies[D]. Hangzhou: Zhejiang University, 2022.
[4] 杨贵军, 周亚梦, 孙玲莉, 等. 基于Benford律的Logistic模型及其在财务舞弊识别中的应用[J]. 统计与信息论坛, 2019, 34(8): 50-56.
YANG G J, ZHOU Y M, SUN L L, et al. Logistic model based on Benford’s law and its application in fraud detection[J]. Journal of Statistics and Information, 2019, 34(8): 50-56.
[5] EL-BANNANY M, DEHGHAN A H, KHEDR A M. Prediction of financial statement fraud using machine learning techniques in UAE[C]//Proceedings of the 2021 18th International Conference on Systems, Signals & Devices, 2021: 649-654.
[6] MOHAMED A H A, SUBRAMANIAN S. Fraud classification in financial statements using machine learning techniques[C]//Proceedings of the 2023 International Conference on IT Innovation and Knowledge Discovery, 2023: 1-4.
[7] PATEL H, PARIKH S, PATEL A, et al. An application of ensemble random forest classifier for detecting financial statement manipulation of Indian listed companies[M]//Recent developments in machine learning and data analytics. Singapore: Springer, 2019: 349-360.
[8] PURDA L, SKILLICORN D. Accounting variables, deception, and a bag of words: assessing the tools of fraud detection[J]. Contemporary Accounting Research, 2015, 32(3): 1193-1223.
[9] DONG W, LIAO S, LIANG L. Financial statement fraud detection using text mining: a systemic functional linguistics theory perspective[C]//Proceedings of the 20th Pacific Asia Conference on Information Systems, 2016: 188.
[10] RAVISANKAR P, RAVI V, RAO G R, et al. Detection of financial statement fraud and feature selection using data mining techniques[J]. Decision Support Systems, 2011, 50(2): 491-500.
[11] LIN C C, CHIU A A, HUANG S Y, et al. Detecting the financial statement fraud: the analysis of the differences between data mining techniques and experts’ judgments[J]. Knowledge-Based Systems, 2015, 89: 459-470.
[12] HAJEK P, HENRIQUES R. Mining corporate annual reports for intelligent detection of financial statement fraud—a comparative study of machine learning methods[J]. Knowledge-Based Systems, 2017, 128: 139-152.
[13] CRAJA P, KIM A, LESSMANN S. Deep learning application for fraud detection in financial statements: IRTG 1792 [R]. Humboldt University of Berlin, 2020.
[14] WU X G, DU S Y. An analysis on financial statement fraud detection for Chinese listed companies using deep learning[J]. IEEE Access, 2022, 10: 22516-22532.
[15] 刘壮, 刘畅, LIN W, 等. 用于金融文本挖掘的多任务学习预训练金融语言模型[J]. 计算机研究与发展, 2021, 58(8): 1761-1772.
LIU Z, LIU C, LIN W, et al. Pretraining financial language model with multi-task learning for financial text mining[J]. Journal of Computer Research and Development, 2021, 58(8): 1761-1772.
[16] QADDOURA R, BILTAWI M M. Improving fraud detection in an imbalanced class distribution using different over-sampling techniques[C]//Proceedings of the 2022 International Engineering Conference on Electrical, Energy, and Artificial Intelligence, 2022: 1-5.
[17] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778.
[18] WANG R, FU B, FU G, et al. Deep & cross network for ad click predictions[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2017: 12.
[19] FU K, CHENG D, TU Y, et al. Credit card fraud detection using convolutional neural networks[C]//Proceedings of the 23rd International Conference on Neural Information Processing. Cham: Springer, 2016: 483-490.
[20] 李淑红, 贾琳. 基于图注意力网络和简单循环单元的化合物-蛋白质交互预测[J]. 模式识别与人工智能, 2021, 34(6): 522-531.
LI S H, JIA L. Compound-protein interaction prediction based on graph attention network and simple recurrent unit[J]. Pattern Recognition and Artificial Intelligence, 2021, 34(6): 522-531.
[21] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision, 2017: 2980-2988.