The United States has been a pioneer in the use of Artificial Intelligence (AI) in the transportation system during the 20th century. Since then, Research and Development in the field of Intelligent Transportation Systems (ITS) has expanded to various nations around the world. Considering that the mortality rate in traffic accidents on highways increases every year, predictive models using machine learning algorithms play an important role in traffic management worldwide. Based on this premise, this research utilized an official database from the Peruvian government on speeding violations detected using speed cameras from 2019 to 2021. Therefore, we employed a quantitative methodology that included a descriptive and trend analysis to identify patterns and compare differences in the fines imposed on major highways in Peru, aiming to develop and validate a predictive model using machine learning algorithms adjusted with hyperparameters that could aid in traffic management and prevent traffic accidents. As results of our research, among the three techniques used - Decision Tree, Random Forest, and Gradient Boosting - it was found that the Gradient Boosting machine learning model would be the most suitable for predicting speeding violations.