Traffic Flow Forecasting Method based on Gradient Boosting Decision Tree

Accurate traffic flow forecasting is very important for intelligent transportation system. This paper proposes a traffic flow forecasting method based on gradient boosting decision tree. In the preprocess phase, sliding time window and feature extension of traffic data are designed on the basis of time series analysis and temporal correlation search is introduced to find prediction training set. In the prediction phase, gradient boosting decision tree is used to predict the traffic flow. Experimental results show that the traffic flow forecasting method based on gradient boosting decision tree is effective and can obtain higher prediction accuracy.