Clustering-Based Travel Pattern for Individual Travel Prediction of Frequent Passengers by Using Transit Smart Card

Abstract

Individual travel prediction is very important for the construction of intelligent urban transportation systems. Previous studies mainly focus on the improvement of algorithms, but pay little attention to the mining of data information. In this paper, the concept of the travel pattern is introduced into the field of individual travel prediction of frequent bus passengers. The travel pattern of passengers refers to the trip with similar boarding time and similar boarding and alighting stations of the same person. Through clustering the travel pattern by DBSCAN algorithm, the regularity of passenger travel can be better exploited and travel information can be integrated into a unified unit as well. In the process of prediction, we first predict whether the passenger will travel, and then, if so, predict the probability distribution of the next trip conditional on the previous one. The proposed method is tested using the Automatic Fare Collection data of Chengdu’s frequent bus passengers in May 2019. Based on travel pattern, the average accuracy of travel information prediction is about 41%, which is 13% higher than the method without using travel pattern. Furthermore, this paper also discusses the influence of spatial threshold in clustering on the prediction results.