presenting the development of the beneish model with emphasis on economic features using neural network, vector machine, and random forest

As the business process becomes more complex, financial statement distortion risk increases. in this regard, researchers have been looking for models to detect fraud in financial statements. beneish (1997) predicted earning manipulation using financial ratios and accruals. since economic pressure is presented as a manager’s external motivation to manipulate income, the beneish model is developed based on economic variables, including inflation rate, gdp growth, exchange rate, and economic growth rate. the fitting of the random forest, vector machine, and neural network was used to fit the extended model. the results show that the accuracy of the random forest model is 99.96% which is more than the neural network and vector models, 96.1% and 93.62%, respectively. the final results show that the developed model is more accurate than the basic beneish model. the results show that economic factors play a significant role in fraudulent financial reporting which should be considered when analyzing financial reporting.