Cluster algorithm based on LDA model for public transport passengers' trip purpose identification in specific area

Abstract

A better understanding of travel demand will enable transit authorities to evaluate the services they offer, adjust marketing strategies and improve overall transit performance. In this paper, we aim to develop a method to identify the trip purpose of passenger flow who have trips to commercial district. While the same region always has the different functions, it is fairly challenging to identify travel patterns for individual transit riders in a large dataset. To this end, we use the Latent Dirichlet Allocation algorithm to generate users' trip topic. And then, with the extraction of user topic distribution as the eigenvectors of the user, we cluster users into groups that have different trip purposes. The performance of the algorithm is compared with those of other prevailing classification algorithms. The results indicate that the proposed method outperforms other commonly used data-mining algorithms in terms of accuracy and efficiency.