Bagging or boosting? Empirical evidence from financial statement fraud detection

Chen, Xiaowei; Zhai, Cong

doi:10.1111/acfi.13159

Cited by 2 publications

(2 citation statements)

References 61 publications

(140 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fortunately, machine learning develops rapidly in recent years, providing efficient approaches to exploring the relationship between financial risks and the growing financial data (Du & Shu, 2022; Li et al, 2022; Wu et al, 2022). Therefore, many scholars are devoted to developing novel fraud detection models using machine learning, such as Logistic Regression, Naive Bayes, Support Vector Machine, Neural Network, Random Forest, Ensemble Method and many more (Song et al, 2014; Cao et al, 2015; Vasarhelyi et al, 2015; Brown et al, 2020; Ding et al, 2020; Bertomeu et al, 2021; Chen & Zhai, 2023; Xu et al, 2023; Achakzai & Peng, 2023; Li et al, 2023; Pan et al, 2023; Riskiyadi, 2023; Rahman & Zhu, 2023; Zhou et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

An intelligent detecting model for financial frauds in Chinese A‐share market

Sun,

Zeng,

et al. 2024

Economics & Politics

View full text Add to dashboard Cite

Financial frauds can cause serious damage to financial markets but are hard to detect manually. In this study, we develop an intelligent detecting model to efficiently identify financial frauds by using XGBoost on raw financial data items in corporation financial statements. With listed companies in Chinese A‐share Market taken as samples, empirical results reveal that the proposed model works better than traditional models by a large margin in detecting fraud. Notably, the proposed model exhibits superior performance when used together with raw financial data items than with financial indicators. Moreover, the proposed model remains robust on outperformance in fraud detection when serial fraud cases are recoded, test periods are altered, more raw financial data are input, as well as other machine learning models–the AdaBoost and SVM–are selected as benchmark models. Our study enriches the application of machine learning in finance sector, and highlights the economic significance of raw financial data as the financial system's most fundamental components.

show abstract

Section: Introductionmentioning

confidence: 99%

An intelligent detecting model for financial frauds in Chinese A‐share market

Sun,

Zeng,

et al. 2024

Economics & Politics

View full text Add to dashboard Cite

show abstract

“…However, it is difficult and uncommon to find accounting irregularities and financial fraud information manually only from financial statements at the surface level. In recent years, many researchers have implemented various approaches to detecting fraud using financial statements, such as analytical procedures, ratio analysis, distribution of scores through artificial neural networks, and checklists to improve the quality and efficiency of fraud detection (Chen, 2023;Rahim, 2023;Wasito, 2023).…”

Section: Introductionmentioning

confidence: 99%

The Impact of Fraud on the Detection of Fraud in Financial Statements and Discretionary Accruals (Meta-Analysis Study)

Narulita,

Baderi,

Hwihanus

2024

aaem

View full text Add to dashboard Cite

This article discusses the impact of fraud-on-fraud detection of financial statements and discretionary accruals through meta-analysis studies. Financial statement fraud is a serious problem that is increasingly prevalent in the global capital market, especially in developing countries such as China. This has driven the need for more sophisticated and effective detection methods. This study aims to identify factors that can affect the detection of financial statement fraud as well as the impact of fraud on the detection of financial statement fraud and discretionary accrual. This article also seeks to find better solutions in dealing with discretionary accruals that can affect investment decisions and public confidence in companies. The findings of the meta-analysis show that factors such as manipulation of accounting records, misrepresentation of information, and errors in the application of accounting principles can affect fraud detection. In addition, the impact of fraud on the detection of fraud in financial statements and discretionary accruals is also discussed comprehensively. This article suggests the need for more dynamic and responsive fraud detection methods to evolving risks.

show abstract

Bagging or boosting? Empirical evidence from financial statement fraud detection

Cited by 2 publications

References 61 publications

An intelligent detecting model for financial frauds in Chinese A‐share market

An intelligent detecting model for financial frauds in Chinese A‐share market

The Impact of Fraud on the Detection of Fraud in Financial Statements and Discretionary Accruals (Meta-Analysis Study)

Contact Info

Product

Resources

About