Predicting Fraudulent Financial Statements with Machine Learning Techniques

Kotsiantis, Sotiris; Koumanakos, Evangelos; Tzelepis, Dimitris; Tampakas, V.

doi:10.1007/11752912_63

Cited by 26 publications

(26 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…After inserting the data set that characterizes the problem, the system automatically uses the corresponding features for training the learning algorithm. In the proposed system, the C4.5 machine-learning algorithm is used as it achieves better accuracy than other models according to our previous study [4]. Moreover, a simple method is used to handle the imbalance problem.…”

Section: Our Ontology-extended Data Sourcementioning

confidence: 99%

See 1 more Smart Citation

Towards an ontology-based system for intelligent prediction of firms with fraudulent financial statements

Kanellopoulos

Kotsiantis²,

Tampakas³

2007

2007 IEEE Conference on Emerging Technologies &Amp; Factory Automation (EFTA 2007)

Self Cite

View full text Add to dashboard Cite

Existing models for facilitating predictions of firms with fraudulent financial statements (FFS) are not semantics-based. The objective of this work was to design an intelligent web portal to serve as service provider for predicting which Greek manufacturing firms issue FFS. The portal serves as a meeting point among manufacturing firms, which are listed on the Athens Stock Exchange (ASE). It has been conceived to help users (e.g., chartered accountants) to detect FFS. The information contained in the portal is dynamically updated and it is related with financial statements. The portal helps users to find Greek manufacturing firms that provide FFS. For this purpose, the knowledge of the formal financial statements domain has been represented by means of ontology, which has been used to guide the design of the application and to supply the system with semantic capabilities. Additionally, the ontological component allows for defining an ontology-guided search engine. The reasoning engine of the proposed system executes logic rules related with well-established financial variables, which characterize a financial statement as fraudulent or not.

show abstract

Section: Our Ontology-extended Data Sourcementioning

confidence: 99%

“…Accounting frauds can be classified as either fraudulent reporting or misappropriation of assets, or both. In this domain, few studies [4] have tested the predictive ability of different types of models and methods used by means of a common data set. Besides, a small number of these models are based on semantic web technologies [5].…”

Section: Introductionmentioning

confidence: 99%

Towards an ontology-based system for intelligent prediction of firms with fraudulent financial statements

Kanellopoulos

Kotsiantis²,

Tampakas³

2007

2007 IEEE Conference on Emerging Technologies &Amp; Factory Automation (EFTA 2007)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Lokanan et al have proposed the use of the Mahalanobis distance to calculate the deviation distance of financial reports, identify abnormal financial reports, and divide them into different credit ratings [20]. Kotsiantis et al have proposed the use of the financial ratio to build a decision tree model to classify financial statements in order to identify false financial statements [21].…”

Section: Research Background and Literature Reviewmentioning

confidence: 99%

A Full Population Auditing Method Based on Machine Learning

Chen¹,

Wu²,

Yan³

2022

Sustainability

View full text Add to dashboard Cite

As it is urgent to change the traditional audit sampling method that is based on manpower to meet the growing audit demand in the era of big data. This study uses empirical methods to propose a full population auditing method based on machine learning. This method can extend the application scope of the audit to all samples through the self-learning feature of machine learning, which helps to address the dependence on auditors’ personal experience and the audit risks arising from audit sampling. First, this paper demonstrates the feasibility of this method, then selects the financial data of a large enterprise for full population testing, and finally summarizes the critical steps of practical applications. The study results indicate that machine learning for full population auditing is able to detect, in all samples, abnormal business whose execution does not adhere to existing accounting rules, as well as abnormal business with irregular accounting rules, thus improving the efficiency of internal control audits. By combining the learning ability of machine-learning algorithms and the arithmetic power of computers, the proposed full population auditing method provides a feasible approach for the intellectual development of future auditing at the application level.

show abstract

“…Kết quả quả nghiên cứu này tương đồng và độ dự báo chính xác hơn so với nghiên cứu của [11,13,19,23]. Kết quả nghiên cứu này phù hợp, đồng thuận với các nghiên cứu của [13,23,28,42], khi cho rằng 3 yếu tố động cơ, cơ hội và thái độ có mối quan hệ với hành vi gian lận BCTC.…”

Section: Kết Quả Nghiên Cứu Và Thảo Luậnunclassified

Nghiên cứu gian lận báo cáo tài chính tiếp cận theo thuật toán rừng ngẫu nhiên

Hung¹

2022

Preprint

View full text Add to dashboard Cite

Nghiên cứu sử dụng các thuật toán rừng ngẫu nhiên dựa trên lý thuyết tam giác gian lận, đểxem xét ảnh hưởng của các yếu tố đến gian lận báo cáo tài chính của các doanh nghiệp ở Việt Nam,sử dụng bộ dữ liệu bảng với 2235 quan sát trong giai đoạn 2014 - 2020. Nghiên cứu xem xét các mức chênh lệch lợi nhuận trước và sau kiểm toán trên 5%. Kết quả dự báo theo thuật toán rừng ngẫu nhiên đạt ở mức 91%. Đồng thời nghiên cứu đã xác định yếu tố ảnh hưởng lớn nhất là sự ổn định tài chính của doanh nghiệp. Nghiên cứu này có giá trị khi ứng dụng trong việc đánh giá tình trạng gian lận báo tài chính của doanh nghiệp khả năng dự báo với độ chính xác cao.

show abstract

Predicting Fraudulent Financial Statements with Machine Learning Techniques

Cited by 26 publications

References 10 publications

Towards an ontology-based system for intelligent prediction of firms with fraudulent financial statements

Towards an ontology-based system for intelligent prediction of firms with fraudulent financial statements

A Full Population Auditing Method Based on Machine Learning

Nghiên cứu gian lận báo cáo tài chính tiếp cận theo thuật toán rừng ngẫu nhiên

Contact Info

Product

Resources

About