Accurate road traffic prediction is necessary for reducing traffic jams and improving urban planning. Current traffic prediction apps, such as Google Maps and HereWeGo, compute and predict traffic based on historical data but do not consider weather conditions, which are equally impactful factors. In this study, to forecast road traffic, we have utilized both historical traffic data and weather data. The study aims to provide insights into the performance of different prediction algorithms for identifying the most practical model for real-world road traffic management. We have used five artificial intelligence algorithms from various categories including AutoRegressive Integrated Moving Average (ARIMA), eXtreme Gradient Boosting (XGBoost), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Hybrid Model, to assess how well they predict traffic flow based on weather and historical data. Eight evaluation metrics, including Accuracy, Precision, Recall, Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Squared Error (MSE), Mean Absolute Percentage Error (MAPE), and R2 (Coefficient of Determination), have been used, along with two real-world datasets. The analysis of every model showed unique advantages and disadvantages. The findings demonstrated that, despite the fact that each model has unique benefits, the XGBoost model outperformed the others in terms of traffic flow prediction accuracy and efficiency.