In this paper, a model is made for the purpose of being a tool in the prediction of road traffic accidents in urban zones of Nuevo León: Monterrey and its metropolitan area; by the means of Artificial Intelligence techniques, such as Artificial Neural Networks. The Maximum Sensitivity Neural Network was developed, trained and validated by using the Scilab development software. The training patterns for the network are a compilation obtained mainly from the INEGI database through the history of road traffic accidents in Nuevo León which took place in 2015. The density of cars transiting municipalities, schedules, types of accidents and causes of accidents are used as input variables to obtain the quantity of traffic accidents as output data. The system uses the 80% of the data to execute the prediction, and the remaining 20% is used to validate the results which further illustrate the analysis of these systems in the prediction of events.