Formulation of Financial Statement Fraud Detection Model Using Artificial Neural Network and Support Vector Machine Approaches in Companies Listed in Tehran Bahador Stock Exchange

Formulation of Financial Statement Fraud Detection Model Using Artificial Neural Network and Support Vector Machine Approaches in Companies Listed in Tehran Bahador Stock ExchangeAbstract:Nowadays, due to the increasing expansion of financial markets and the need to attract domestic and foreign investors, one of the most important concerns of any company is to finance the correct disclosure of financial information. Artificial and support vector machines were listed at companies listed on the Tehran Stock Exchange. The present study is a kind of applied and empirical-correlation research. The statistical population includes the companies listed in the Tehran Stock Exchange during the period 1972-1999. Recent research has shown that investors in the decision-making process select companies whose profitability is higher and in fact higher quality. The results showed that in the training section the predictive power of the support vector algorithm was about 86% and in the test about 82%. Also, the prediction power of neural network algorithm was 81% in training and 78% in test.