Machine Learning for public transportation demand prediction: A Systematic Literature Review

Within the Intelligent Public Transportation Systems (IPTS) field, the prediction of public transportation demand is a key point for enhancing the quality of the services. These predictions can be exploited by transit operators, for service planning and management, as well as by passengers, for planning their trips. Hence, the public transportation demand prediction problem is being more and more investigated by the scientific community, with several different proposals in terms of Machine Learning (ML) techniques, employed sensors, considered external features, and so on. However, there is a lack of comprehensive reviews that summarize and organize the available proposals on this topic. Hence, researchers intending to propose novel ML solutions, and practitioners willing to implement such solutions, may be overwhelmed by the plethora and heterogeneity of scientific work. To support these kinds of profiles, in this paper, we provide a Systematic Literature Review on ML techniques for predicting public transportation demand. This review highlights a growing interest by the scientific community on this topic, but also the lack of open datasets (useful for benchmarking), and in general of reproducible studies. Moreover, while deep learning techniques are frequently favored for their potential in terms of accuracy, associated costs, interpretability, and energy consumption are often overlooked.