Hierarchical prediction based on two-level Gaussian mixture model clustering for bike-sharing system

• Published in: Knowledge-based systems 2019-08, Vol.178, p.84-97
• Main Authors: Jia, Wenzhen, Tan, Yanyan, Liu, Li, Li, Jing, Zhang, Huaxiang, Zhao, Kai
• Format: Article
• Language: English
• Subjects: Algorithms; Bicycles; Bike-sharing system; Clustering; Error reduction; Gaussian mixture model clustering; Geographical locations; Migration; Migration trend; Probabilistic models; Regression analysis; Stations; Traffic prediction; Upgrading
• ISSN: 0950-7051; 1872-7409
• DOI: 10.1016/j.knosys.2019.04.020

Recently, there is a new approach for bike usage that has emerged by bike-sharing system. While traveling on the road, more and more people will choose to ride shared bicycle at home and abroad. When using shared bikes, we also face to problems and challenges. As a result of the shared-bikes renting/returning at different stations in different periods are imbalanced, the bike-sharing system needs to be updated frequently. This is the motivation for our study of bike-sharing traffic prediction. In this paper, we propose a hierarchical prediction model that predicts the number of rents/returns to each cluster in a future period to achieve redistribution. Firstly, we propose a two-level Gaussian Mixture Model clustering algorithm to divide bike stations into groups where migration trends of bikes among stations as well as geographical locations information are considered. Secondly, we employ a gradient boosting regression tree to predict the entire traffic rents. Thirdly, we use a multi-similarity-based inference model to forecast the check-out proportion and inter-cluster transition. Based on the above, finally the rents/returns of bikes to each cluster are deduced. In order to verify the effectiveness of our hierarchical prediction model, we validate it on the bike-sharing system of New York City (NYC) and Washington D.C. (D.C.) respectively, and compare the results with those of other popular methods obtained. We prove that our method is robust. Experimental results demonstrate the superiority over other methods. Compared with the state-of-the-art model, our model reduces the error rate roughly by 8%and 22% respectively in the check-out and check-in prediction for NYC, and reduces roughly by 3%and 2% respectively in the check-out and check-in prediction for D.C. Compared with other baseline models, our model can reduce the error rate roughly by 20%and 30% respectively in the check-out and check-in prediction for the two cities.