Today, travel time prediction is essential for passengers who can easily access information and want to be able to plan their journeys as well as their daily activities. Travel time varies due to some unpredictable external factors especially in big cities. Therefore this paper proposes a powerful but simple Machine Learning (ML) model by using data collected by GPS devices. The model uses a Multiple Linear Regression algorithm that learns from historic data and predicts future data for each bus stop interval by considering external factors such as; weather condition, peak hours, busy week days and busy days of year. A simulation model was developed to validate the model. Then the simulation model was compared to average of historic data and real data. Results show that the prediction model outperforms the average model and calculates closest travel times to the real data.