The rapid development of urbanization and transportation has resulted in an increasingly more severe traffic congestion in metropolitan areas. In order to overcome this challenge, this research study integrates machine learning techniques to develop a precise traffic congestion prediction model. Random Forest, known for its robustness, high performance, and applicability, considers a set of data variables such as climate conditions, time of day, and road quality. Here, the proposed model that makes use of both SVM and Random Forest algorithms results in a lower mean squared error rate and high accuracy in forecasting traffic conditions. The research findings demonstrate that machine learning methods might serve to enhance how traffic is directed and transportation infrastructure made safer and effective. This research study compares machine learning models with one another and computes the mean absolute error for each to determine the best prediction. In this model, the random forest algorithm and SVM algorithm demonstrate the accuracy (87.84%) and error (12.16%) compared to the other existing models.