Traffic Congestion Prediction Using Machine Learning Techniques
This work addresses traffic management for urban planners and commuters, but it is incremental as it builds on existing prediction methods with added weather factors.
The paper tackles traffic congestion prediction by developing a model that incorporates weather data, achieving an average RMSE of 1.12 for predicting congestion one week ahead using New Delhi traffic data.
The prediction of traffic congestion can serve a crucial role in making future decisions. Although many studies have been conducted regarding congestion, most of these could not cover all the important factors (e.g., weather conditions). We proposed a prediction model for traffic congestion that can predict congestion based on day, time and several weather data (e.g., temperature, humidity). To evaluate our model, it has been tested against the traffic data of New Delhi. With this model, congestion of a road can be predicted one week ahead with an average RMSE of 1.12. Therefore, this model can be used to take preventive measure beforehand.