<scp>TaxiBJ21</scp>: An open crowd flow dataset based on <scp>Beijing</scp> taxi <scp>GPS</scp> trajectories
Weiwei Jiang
Abstract
Crowd flow prediction has been a significant problem in smart cities. Real‐world datasets are the basis of designing data‐driven models, for example, machine learning and deep learning models. However, some well‐known datasets, for example, TaxiBJ, become unavailable when the original sharing links are deleted as the data providers move to new jobs. As an alternative choice, TaxiBJ21 is proposed in this letter for future crowd flow prediction studies. This new open dataset contains the taxi inflow and outflow matrices in Beijing for 3 months, with the same data format as TaxiBJ and can be used in the current literature seamlessly. In this letter, the process of constructing TaxiBJ21 is introduced and three baselines including two simple historical models and a multilayer perceptron neural network are evaluated on this new dataset as benchmarks. Both the data and baselines are publicly available in a Github repository.