Using the Road Traffic Prediction Dataset and the PeMS dataset, this study assesses the traffic prediction performance of machine learning (ML) and deep learning (DL) models. These datasets were used to train and evaluate a variety of machine learning and deep learning models, such as MLP NN, Gradient Boosting, Random Forest, GRU, LSTM, Linear Regression, and Stochastic Gradient. The models' accuracy was evaluated using performance measures such Explained Variance (EV) score, Root Mean Squared Error (RMSE), R-squared (R2), and Mean Absolute Error (MAPE). The outcomes demonstrate the efficacy of MLP NN and Gradient Boosting in traffic prediction, with the former performing well on both datasets. The study emphasizes how crucial model selection and dataset selection are to enhancing traffic management system forecast accuracy.