Growing towns and cities have always struggled with traffic congestion. Therefore, in the field of intelligent transportation management systems, traffic prediction is crucial. This study investigates whether traffic pattern prediction using machine learning techniques is feasible. The Gradient Boosting model is used to estimate the flow of urban traffic. The model uses generic features, such as date, time, and holiday information, for prediction. The presence of precipitation and snowfall is known to have a substantial impact on traffic conditions, hence weather-related features like snow, precipitation, and weather description are also included in the model.