Traffic Flow Prediction Based on Explainable Machine Learning

Abstract

Traffic flow prediction is one of the important links to realize an urban intelligent transportation system. Thanks to the in-depth research of artificial intelligence theories, the machine learning method has been widely used in intelligent transportation engineering. However, due to the “black box” as its characteristics, its application and further development are limited. Exploring the explainability of machine learning models in traffic flow prediction is an important issue to make it more reliable in traffic engineering and other practical applications. Apart from selecting the RandomForest model and the CatBoost model as the objects to research the traffic flow prediction against temporal and spatial changes, this paper makes a comprehensive evaluation and comparison with LightGBM and the other two prediction models through different indicators. Meanwhile, aiming at the low explainability of the models, their feature importance is analyzed and compared with reality. The results show that the RandomForest model and CatBoost model make good predictions, whose feature importance is consistent with the actual situation, verifying their explainability.