چکیده:
Fraud is a common phenomenon in business, and according to Section 24 of the Iranian Auditing Standards, it is the fraudulent act of one or more managers, employees, or third parties to derive unfair advantage and any intentional or unlawful conduct. Financial statements are a means of transmitting confidential management information about the financial position of a company to shareholders and other stakeholders. In this paper, by reviewing the literature, 6 indicators of current ratio, debt ratio, inventory turnover ratio, sales growth index, total asset turnover ratio, and capital return ratio as input and detection of financial fraud as output are considered for the fuzzy neural network. The database was compiled for 10 companies in the period from 2010 to 2018 after clearing and normalizing qualitatively between 1 to 5 discrete numbers with very low or very high meanings, respectively. The fuzzy neural network model with 161 nodes, 448 linear parameters, 36 nonlinear parameters, and 64 fuzzy laws with two methods of accuracy approximation of mean squared error and root mean squared error has been set to zero and 0.0000001 respectively. This neural network can be used for prediction.
خلاصه ماشینی:
Predicting Financial Statement Fraud Using Fuzzy Neural Net- works Mohsen Rostamy-Malkhalifeha,*, Maryam Amirib, Mehrdad Mehrkamc a Department of Mathematics, Science and Research Branch, Islamic Azad University, Tehran, Iran b Department of Management and Economics, Science and Research Branch, Islamic Azad University, Tehran, Iran c Department of Management and accounting, Allameh Tabataba’i University, Tehran, Iran ARTICLE INFO ABSTRACT Fraud is a common phenomenon in business, and according to Section 24 of theIranian Auditing Standards, it is the fraudulent act of one or more managers, em- ployees, or third parties to derive unfair advantage and any intentional or unlawful conduct.
In this paper, by reviewing the literature, 6 indicators of cur- rent ratio, debt ratio, inventory turnover ratio, sales growth index, total asset turn- over ratio, and capital return ratio as input and detection of financial fraud as output are considered for the fuzzy neural network.
Sharma and Panigrahi [15] studied the detection of fraud in financial systems based on data mining methods.
Also, methodologically this is an analytical study, because, all the theories, laws, principles, and techniques that detect fraud and corruption of financial statements using a fuzzy neural network, are used to solve executive problems [17].
Important parameters for fuzzy neural network modeling to detect financial statement fraud are [21]: Input variables: X1 = Current Ratio X2 = Debt Ratio X3 = Inventory turnover ratio X4 = Sales Growth Index X5 = Total asset turnover ratio X6 = Capital return ratio Output variable: 1 = Fraud 0 = Non-Fraud The fuzzy neural network is an adaptive fuzzy inference system based on artificial neural networks that is widely used to study phenomena with nonlinear equations.