With the continuous development of intelligent transportation systems (ITSs), traffic flow prediction methods have become the cornerstone of this technology. This paper comprehensively reviews the traffic flow prediction methods used in ITSs and divides them into three categories: statistics-based, machine learning-based, and deep learning-based methods. Although statistics-based methods have lower data requirements and machine learning methods have faster calculation speeds, this paper concludes that deep learning methods have the best overall effect after a comprehensive analysis of the principles, advantages, limitations, and practical applications of each method. Deep learning methods can overcome many limitations that traditional statistical methods and machine learning methods cannot surpass, such as the ability to model complex nonlinear relationships. Experimental results show that hybrid neural networks are significantly superior to traditional methods in terms of their prediction accuracy and generalization abilities. By combining multiple models and techniques, hybrid neural networks can improve the accuracy of traffic flow prediction under different conditions. Although deep learning methods have achieved remarkable success in short-term prediction, challenges still exist, such as the generalization of models in different traffic scenarios and the difficulty of long-term traffic flow prediction. Finally, this paper discusses future research directions and anticipates the future development of ITS technology.

With the ongoing development of Intelligent Transportation Systems (ITS), traffic flow prediction methods have become a cornerstone of its technology. Accurate traffic flow forecasting can significantly support traffic management and decision-making.However, the expanding demand for such systems presents new challenges for the development of traffic flow prediction technologies. This paper offers a comprehensive review of traffic flow prediction methods utilized in ITS, classifying them into three categories: statistical-based, machine learning-based, and deep learning-based methods. By analyzing the principles, advantages, limitations, and applications of each approach within ITS, and comparing them through practical case studies, the paper emphasizes the pivotal role of deep learning models in improving prediction accuracy, particularly in short-term traffic forecasting. Despite the notable success of deep learning methods in short-term predictions, challenges persist, such as model generalization across diverse traffic scenarios and difficulties in long-term traffic flow forecasting. The paper concludes by suggesting future research directions, aiming to provide new perspectives and enhance the development of ITS technologies.