Capturing the conditions that introduce systematic variation in bike-sharing travel behavior using data mining techniques

Bordagaray, Maria; dell�Olio, Luigi; Fonzone, Achille; Ibeas, �ngel

Abstract

The potential of smart-card transactions within bike-sharing systems (BSS) is still to be explored. This research proposes an original offline data mining procedure that takes advantage of the quality of these data to analyze the bike usage casuistry within a sharing scheme. A difference is made between usage and travel behavior: the usage is described by the actual trip-chaining gathered with every smart-card transaction and is directly influenced by the limitations of the BSS as a public renting service, whilst the travel behavior relates to the spatio-temporal distribution, the travel time and trip purpose. The proposed approach is based on the hypothesis that there are systematic usage types which can be described through a set of conditions that permit to classify the rentals and reduce the heterogeneity in travel patterns. Hence, the proposed algorithm is a powerful tool to characterize the actual demand for bike-sharing systems. Furthermore, the results show that its potential goes well beyond that since service deficiencies rapidly arise and their impacts can be measured in terms of demand. Consequently, this research contributes to the state of knowledge on cycling behavior within public systems and it is also a key instrument beneficial to both decision makers and operators assisting the demand analysis, the service redesign and its optimization.

Citation

Bordagaray, M., dell’Olio, L., Fonzone, A., & Ibeas, Á. (2016). Capturing the conditions that introduce systematic variation in bike-sharing travel behavior using data mining techniques. Transportation Research Part C : Emerging Technologies, 71, 231-248. https://doi.org/10.1016/j.trc.2016.07.009

• Journal Article Type: Article
• Acceptance Date: Jul 24, 2016
• Online Publication Date: Aug 10, 2016
• Publication Date: 2016-10
• Deposit Date: Aug 10, 2016
• Publicly Available Date: Feb 11, 2018
• Journal: Transportation Research Part C: Emerging Technologies
• Print ISSN: 0968-090X
• Electronic ISSN: 1879-2359
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 71
• Pages: 231-248
• DOI: https://doi.org/10.1016/j.trc.2016.07.009
• Keywords: Bike-sharing systems, data mining, smart-card data, demand analysis, cycling, trip-chaining,
• Public URL: http://researchrepository.napier.ac.uk/Output/336831
• Contract Date: Aug 10, 2016