Financial Feature Embedding with Knowledge Representation Learning for Financial Statement Fraud Detection

Shen, Yuming; Guo, Caichan; Li, Huan; Chen, Junjie; Ye, Guo; Qiu, Xinying

doi:10.1016/j.procs.2021.04.110

Cited by 14 publications

(12 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Therefore, choose the appropriate financial fraud early warning indicators to establish a suitable model foundation. In the process of selecting indicators, follow the principles of reference, systematization, operability, and loose before tightening to make the model have good versatility [12][13][14]. The premise of an efficient and accurate deep learning model is to select good financial fraud characteristic variables, and the index selection is shown in Fig.…”

Section: Construction Of Financial Fraud Prevention Model Based On De...mentioning

confidence: 99%

See 1 more Smart Citation

Research on the Model of Preventing Corporate Financial Fraud under the Combination of Deep Learning and SHAP

Wang¹

2023

IJACSA

View full text Add to dashboard Cite

Preventing financial fraud in listed companies is conducive to improving the healthy development of China's accounting industry and the securities market, is conducive to promoting the improvement of the internal control system of China's enterprises, and is conducive to promoting stability. Based on the combination of SHAP (Shapley Additive explanation), a prediction and identification model should be built to determine the possibility of financial fraud and the risk of fraud for the company. The research model has effectively improved the identification accuracy of financial fraud in listed companies, and the research model has effectively dealt with the gray sample problem that is common in the forecasting model through the LOF algorithm and the IF algorithm. When conducting comparative experiments on the models, the overall accuracy rate of the research model is over 85%, the recall rate is 78.5%, the precision rate is 42%, the AUC reaches 0.896, the discrimination degree KS reaches 0.652, and the model stability PSI is 0.088, compared with traditional financial fraud Forecasting models FS model and CS model has a higher predictive effect. In the empirical analysis, selecting a company's fraud cases in 2020 can effectively analyze the characteristic contribution in the fraud process and the focus on fraud risks. The established model can effectively monitor the company's finance and prevent fraud.

show abstract

Section: Construction Of Financial Fraud Prevention Model Based On De...mentioning

confidence: 99%

“…The study method is based on the forward distribution algorithm to achieve the integration of the additive model. The iterative process of the traditional GBRT algorithm is shown in formula (13). The gradient boosting process of the XGBoost model is shown in Fig.…”

Section: B Construction Of Financial Anti-fraud Model Based On Deep L...mentioning

confidence: 99%

Research on the Model of Preventing Corporate Financial Fraud under the Combination of Deep Learning and SHAP

Wang¹

2023

IJACSA

View full text Add to dashboard Cite

show abstract

“…Previous studies have already realized the complexity of the imbalance problem [66][67][68], and provided various solutions including over-sampling [69], under-sampling [26,[70][71][72] and synthetic minority over-sampling technique (SMOTE) [64]. However, most of the experimental results seem to be less reliable for the reason of data preprocess measures.…”

Section: B Imbalance Data Treatmentmentioning

confidence: 99%

An Analysis on Financial Statement Fraud Detection for Chinese Listed Companies Using Deep Learning

2022

IEEE Access

View full text Add to dashboard Cite

Financial fraud has extremely damaged the sustainable growth of financial markets as a serious problem worldwide. Nevertheless, it is fairly challenging to identify frauds with highly imbalanced dataset because ratio of non-fraud companies is very high compared to fraudulent ones. Intelligent financial statement fraud detection systems have therefore been developed to support decision-making for the stakeholders. However, most of current approaches only considered the quantitative part of the financial statement ratios while there has been less usage of the textual information for classifying, especially those related comments in Chinese. As such, this paper aims to develop an enhanced system for detecting financial fraud using a state-of-the-art deep learning models based on combination of numerical features that derived from financial statement and textual data in managerial comments of 5130 Chinese listed companies' annual reports. First, we construct financial index system including both financial and non-financial indices that previous researches usually excluded. Then the textual features in MD&A section of Chinese listed company's annual report are extracted using word vector. After that, powerful deep learning models are employed and their performances are compared with numeric data, textual data and combination of them, respectively. The empirical results show great performance improvement of the proposed deep learning methods against traditional machine learning methods, and LSTM, GRU approaches work with testing samples in a correct classification rate of 94.98% and 94.62%, indicating that the extracted textual features of MD&A section exhibit promising classification results and substantially reinforce financial fraud detection.

show abstract

“…The drawback was higher time complexity. Shen et al 25 presented the fraud identification in financial statement based on embedding financial features (FF) and learning the knowledge representations. The traditional features were combined with knowledge graph (KG) models to learn newer representations augmented with embedded features of diverse financial classes.…”

Section: Related Workmentioning

confidence: 99%

Unsupervised learning for financial statement fraud detection using manta ray foraging based convolutional neural network

Yadav

Sora

2022

Concurrency and Computation

View full text Add to dashboard Cite

Summary Financial statement fraud detection is a significant topic and a challenging task related to countless applications such as financial sectors, insurance, government agencies, law enforcement and so on. This article presents an unsupervised learning model to identify the financial fraud statements using the hybrid convolutional neural network. The fraud detection scheme can be performed using a few stages: data preprocessing, sampling, feature extraction, feature selection, clustering, and classification methods. The preprocessing and sampling processes are used to clean and recognize duplicate data. Then, the proposed model analyzes both text features and financial variables to provide the best classification of financial statement fraud. In this article, a new fuzzy red deer's algorithm is proposed for selecting the optimal feature set, which can improve the classification accuracy of the fraud prediction model. Subsequently, an adaptive density based clustering (ADBC) approach is introduced for labeling the selected features through the clustering process. Finally, the fraud statements are predicted by proposing a hybrid CNN‐MRFO model wherein the hyperparameters of the CNN model are optimized through the MRFO learning algorithm. The simulation results prove the effectiveness of the proposed model in terms of accuracy (98.85%), precision (98.62%) and F‐measure (99.32%).

show abstract

Financial Feature Embedding with Knowledge Representation Learning for Financial Statement Fraud Detection

Cited by 14 publications

References 12 publications

Research on the Model of Preventing Corporate Financial Fraud under the Combination of Deep Learning and SHAP

Research on the Model of Preventing Corporate Financial Fraud under the Combination of Deep Learning and SHAP

An Analysis on Financial Statement Fraud Detection for Chinese Listed Companies Using Deep Learning

Unsupervised learning for financial statement fraud detection using manta ray foraging based convolutional neural network

Contact Info

Product

Resources

About