Identifying the Financial, Economic and Structural Components Effective in Preventing Financial Frauds

 The aim of the present study is to identify the financial, economic and structural components effective in preventing financial frauds. Heeding the issue of fraudulent financial reporting in the country, considering the increase in the number of companies admitted to the Tehran Stock Exchange, the membership of the Stock Exchange and Securities Organization among the members of the International Organization of Securities Commissions, the requirement to improve the quality of financial information, special attention to attracting foreign investors are deemed necessary in the post-sanction conditions and the continuation of the privatization process in the country. The statistical population of this study is all the companies accepted in the Tehran Stock Exchange from 2010 to the end of 2011, and their number is 570 companies. The hypothesis of the research is to evaluate the effectiveness of discovering the possibility of fraud in financial statements using the Morchegan algorithm in comparison with the regression method, neural network, K average and genetic algorithm. The results indicate that the performance of the Morchegan algorithm is based on entropy in the correct classification. Companies are similar to the performance of the genetic algorithm. The error in the classification of companies in the entropy-based Morchegan algorithm is significantly more than the error in the classification of companies using logistic regression methods and the neural network algorithm. The distance-based Morchegan algorithm is significantly more unsuccessful than the logistic regression method in correctly identifying companies as suspected fraud companies.