Driving violations is one of the most important social issues in the world, and especially in developing countries. According to the World Health Organization, as a result of driving violations, 2.1 million people die annually, between 20 and 50 million People are injured and more than $ 540 billion in financial damage and is projected to double in the next 20 years. Driving in Iran is also a matter of concern. The purpose of this study is to investigate the effective factors of violations Research population: The statistical population includes offenders who have committed violations in one year in 1997 and have 1450 records. The data are extracted from the data in the Navigator's system and presented as a descriptive survey in a survey method. It is done using artificial neural networks. Initially, using extensive research and study literature in the area of crime analysis, it has been devised from internal and external authoritative sites to determine the effective factors in driving crime analysis. In the second step, the use of Artificial Neural Network method with MATLAB software has been dealt with and The multilevel neural network model is selected and the third step is validated and validated. Conclusion: The three-layer neural network has better results and the target network is more in line with actual data.