Presenting a fraud prediction model based on artificial intelligence (support vector machine (SVM) model)

In today's world, along with the advancement of technology, the application of data science and artificial intelligence in all fields, including accounting, is undeniable. Artificial intelligence has been widely used in accounting science in various topics, including internal accounting process, reports related to income and expenses, and even detection and prediction of fraud, which actually results in higher speed and reliability as a result of eliminating human error are. Therefore, in this research, the aim is to investigate the effectiveness of the support vector machine method in predicting fraud. In this regard, in the period from 2015 to 2015, the number of 136 companies admitted to the stock exchange was examined in this way. The results show that this model with an accuracy factor of 85%, a readability factor of 97% and an accuracy of 83% has an acceptable efficiency in predicting fraud, and its output shows that the total assets of the previous period, operating cash flow and also, the fixed assets of the previous period had the greatest effect on committing fraud