In this paper, the fraud detection model in financial statements is examined by using the financial ratios tool. The purpose of the fraud detection model is to examine the financial statements using the financial instrumnet tool. The period of this research is considered to be 1339-1394. The statistical population includes all companies accepted in Tehran Stock Exchange. The statistical sample consisted of 35 healthy companies with healthy, non fraudulent statements in the Tehran Stock Exchange, which had been listed on the Stock Exchange before 1387, and during this period, at least once in the list of the Top Vocational Companies Declared by the Stock Exchange. Research in terms of the purpose of the theoretical type and in terms of analytical-experimental methodology. In order to investigate the relationship between independent variables and dependent variable, two – way independent t-test and Mann-Whitney test as well as developed logistic regression model were used. The results of the research showed that by using the financial statements analysis of listed companies Securities can be discovered in fraudulent financial reporting. The results of the research indicate that all financial ratios include the ratio of total debt to total assets, the ratio of liquidity to current debt, the financial ratios of current assets to current debt, and the ratio of net profit to equity in determining fraud. Has an effective role.

Purpose: Accounting fraud is a serious misconduct that harms the confidence of investors in the capital market and is one of the controversial topics in the financial field. Many researches have examined the effect of fraud on the capital market from different aspects, but it is still not clear whether the disclosure of frauds committed by companies in the past affects the risk of future stock price crash. Therefore, the purpose of this research is to investigate the relationship between the detection of fraud in financial statements by market participants and the risk of crashing future stock prices.Method: In order to achieve the goal of the research, 143 companies were selected among the companies admitted to the Tehran Stock Exchange during the years 1392 to 1400 by systematic elimination method and a total of 1287 company-years were considered.Results: The findings of the research show that fraud in the financial statements of companies and its detection by market participants has a positive and significant effect on the risk of crashing stock prices.Conclusion: The findings of this research show that following the disclosure of accounting frauds and the accumulation of bad news by the company and the deterioration of the quality of the disclosure and the vagueness of the information environment of the company, the trust of the investors has been lost and in turn lead to It is the risk of crashing stock prices. This supports our theoretical mechanism that accounting fraud affects stock price crash risk through information opacity.Contribution: This research can help investors to investigate the information environment of companies more deeply and understand the power of information environment of companies in their financial decisions.

Fraud is one of the key factors in decreasing the reliability of reports and financial statements, which in turn, has increased the risk and cost of business, reduced the investors’ confidence, and put the validity and integrity of the accounting profession into question. The purpose of this paper is to rank factors affecting the probability of financial fraud, according to Audited Financial Statements for 181 firms listed in Tehran Stock Exchange for 9 years (2006 to 2014). Finally, the questionnaires prepared by experts were analyzed through analytic hierarchy process (AHP). As a result, we found that paragraphs related to overstated or understated income or assets have the highest priority in the factors affecting the probability of financial fraud, according to Audited Financial Statements.

Objective: The main purpose of this study is to analyze fraud in financial statements and new techniques used to discover it in financial statements of Iran stock exchange. Method: This research is a descriptive research in which to analyze and interpret the types of fraud in financial statements and new techniques used to discover it. Results: In today's competitive world, organizations face a huge amount of data, and one of the major issues that needs to be addressed, is the issue of financial statement fraud. Because it cause lack of transparency about operations of the company and cause issues such as asset misappropriation, loss of company credit and so on. Conclusion: Fraud detection approaches generally include Bayesian Process and Networking approaches for detecting commodity and securities fraud; Bayesian Networking approaches, Genetic Algorithm etc to detect financial statements fraud; machine learning approaches, decision tree etc to detect credit card fraud and logistic regression approach to detect insurance fraud. As a result, all groups involved in fraud detection need these tools and approaches to detect fraud in a timely manner and to inform managers to track and resolve them. In addition, accountants, auditors and managers need to be familiar with new approaches to fraud detection for metadata analysis, thereby analyzing all the risk-related signs of fraud detection and achieving a more rational and transparent result.

This study aims to identify the best financial ratios and the most efficient method for fraud risk detection in the financial statements of the listed companies by considering the financial importance of decision-making as well as the growing fraud statistics and detrimental effects. The statistical sample included 180 companies listed in the Tehran Stock Exchange from 2014 to 2021 (532 fiscal years suspected of fraud and 908 non-fraudulent fiscal years). Theoretical foundations were first taken into account to extract 96 financial ratios. The k-NN algorithm, Bayesian network, support vector machine, and bagging method were then employed for fraud risk detection in financial statements. According to the findings, the adopted methods failed to meet the evaluation standards in general. With an accuracy of 70. 60% and a proportionality function value of 0. 2940, the gray wolf optimization (GWO) algorithm was then utilized to reduce the ratios in order to improve performance. After 31 iterations, nine appropriate financial ratios were determined. The extracted financial ratios were then used to reevaluate the effectiveness of the proposed fraud detection strategies. After the financial ratios were reduced, all of the proposed approaches yielded better results. The accuracy and efficiency of the bagging method, support vector machine, Bayesian network, and k-NN algorithm were reported 79. 25% and 81. 70%, 75. 83% and 80. 30%, 72. 01% and 74. 60%, and 74. 55% % and 75. 60%, respectively. In conclusion, the bagging method outperformed the other approaches in terms of accuracy and efficiency.

This paper aims the detection of financial statements fraud according to audit report of financial statments. The initial research data were collected from a statistical sample consisting of 164 companies, listed in the Tehran Stock Exchange from 2014 to 2017 and selected through the systematic sampling method. The statistical sample was divided into two separate groups, i. e. fraudulent (1) and non-fraudulent (0) companies. The independent fraud-related variables included 41 financial and nonfinancial variables, selected through theoretical foundations and the research background. The data of variables, collected through the desk method, were finally analyzed through the top five techniques of machine learning, including; the Bayesian networks, the decision tree, artificial neural networks, support vector machine, and combined method. According to the results, all of these techniques were highly capable of fraud detection in financial statements. Moreover, the proposed combined technique outperformed the other techniques in evaluation accuracy and power with an estimation rate of 96. 2%.

AbstractFinancial statement fraud has become a serious problem for market participants and policy makers. In fact, it threatens the reliability of capital markets, corporate executives and even the auditing profession. The purpose of this study is to use the approach of dynamic averaging models to predict fraud in financial statements.The present research is applied in terms of method. The research period is 1390 to 1399 and in estimating the model, the data of selected companies in Tehran Stock Exchange has been used.Using the systematic elimination approach, the research sample size of 125 companies was selected. To estimate the model, MATLAB 2021 software has been used.In this research, based on the dynamic averaging model, we predicted the fraud and accuracy of the estimation models. Based on the results of asset return variables; Return on equity; Operating profit margin; Asset turnover ratio and operating cash-to-sales ratio have a negative effect on fraud and other variables have a positive effect.

The current era is known as the "age of information," and the capital market is built on information as the economy's primary engine. The system of financial statements of corporations, which is the most significant source of information used in the capital market, produces an information system called accounting. Fraud and manipulation in these financial statements raise corporate risk, erode investor confidence, and cast doubt on the objectivity of accounting experts. Owing to the significance of fraud, this study aims to offer a way to foretell the likelihood of fraud in the financial statements of businesses admitted to the Tehran Stock Exchange between 2014 and 2021. 180 enterprises listed on the stock exchange make up the statistical sample (532 years of companies - suspected fraud years and 908 years - of non-fraudulent companies). According to the independent auditor's assessment, the existence of dormant assets and items, the doubting of the assumption of continuity of activity, the presence of tax discrepancies with other tax areas, and the dearth of adequate performance tax reserves led to the selection of the companies suspected of fraud. 96 financial ratios have been compiled by examining the theoretical foundations and research. In this research, the supervised methods of support vector machine, K-nearest neighbor, Bayesian network, neural network, decision tree, logistic regression, random forest and the hybrid method (bagging) have been used. The results of the research showed that the performance evaluation criteria of precision, accuracy, sensitivity, and F-Measure and efficiency (ROC) and the accuracy result of the confusion matrix in the combined method (bagging) were 72.45, 61.21, 64.74, 62.93, 73.50, and 72.45 percent, respectively, which indicates the better performance and greater ability of this method to predict the possibility of fraud in financial statements compared to other proposed methods.

This paper introduces knowledge as a valuable resource for assessment and prediction. Providing a solution to identify fraud increases the accuracy and fraud companies. The proposed solution is a full-time detection method that does not require human resources and the system does it. Financial statement fraud has become an increasingly serious problem for businesses, governments and investors, and the variables that affect fraud are financial and non-financial variables. The data collected based on the CRISP approach were the top four techniques among other techniques.

The overall purpose of publishing financial statements is to provide information about financial status, performance results, and cash flows to stakeholders. Users' trust, especially investors, shareholders, and creditors, with the information in these statements is an incentive that leads one to fraud in financial reporting. The purpose of present research is to predict fraud in fraudulent financial statements fraud. This triangle is based on the assumption that one is motivated to commit fraud when there are three elements of fraud. These three elements are 1. some perceived motivations for fraud, 2. some opportunities for fraud, and 3. methods of reasoning that fraud does not harm the value of the perpetrator (Cressey, 1973). In this study, the dependent variable of financial statement fraud is used by the researcher as a substitute for earnings management (profit). Independent variables include the pressure of financial stability, the greed of the perpetrator, ineffective supervision, effective supervision, the pressure of external expectations, and predicted financial goals. The statistical population of the study is listed companies in Tehran Stock Exchange and the statistical sample of 98 companies is selected through systematic elimination method during the years 2012-2018. The results of testing the research hypotheses using multivariate regression model and panel data model showed that the pressure of financial stability has a significant relationship with financial statements Fraud.