Exploring patterns of demand in bike sharing systems via replicated point process models

• Published in: Journal of the Royal Statistical Society Series C: Applied Statistics Vol. 68; no. 3; pp. 585 - 602
• Main Authors: Gervini, Daniel, Khanal, Manoj
• Format: Journal Article
• Language: English
• Published: Oxford Wiley 01-04-2019; Oxford University Press
• Subjects: Bicycles; Clustering; Demand; Fleet management; Functional canonical correlation; Functional principal components; Hierarchical clustering; Parameter estimation; Poisson process; Spline smoothing; Stations
• ISSN: 0035-9254; 1467-9876
• DOI: 10.1111/rssc.12322

Understanding patterns of demand is fundamental for fleet management of bike sharing systems. We analyse data from the Divvy system of the city of Chicago. We show that the demand for bicycles can be modelled as a multivariate temporal point process, with each dimension corresponding to a bike station in the network. The availability of daily replications of the process enables non-parametric estimation of the intensity functions, even for stations with low daily counts, and straightforward estimation of pairwise correlations between stations. These correlations are then used for clustering, revealing different patterns of bike usage.