Perceptually important points of mobility patterns to characterise bike sharing systems: The Dublin case

Abstract

Since the first Bike Sharing System (BSS) was introduced in Amsterdam (1965), studies about BSSs have constantly increased. BSSs studies are typically focused on user's socio-economic characteristics, bike sharing patterns and purpose of use in the city. This paper increases the knowledge of bike station classification due to users' mobility patterns based on data mining tools. For this purpose stations will be identified by a code based on joining three ratios: the load factor or number of available bikes ratio, the cumulative trips ratio, and the turnover station ratio. The latter is the new ratio proposed in this paper, which measures the effectiveness degree of each station. The higher the rate, the more effective the station is. Data mining tools to work with these three ratios are used in the proposed algorithm. Specifically, the perceptually important points (PIP) process to represent and index each time series of each station, and a rule set to classify the stations, are used. The results could support planning and operations decisions for re-design and management of BSSs in relation to the spatial implications of the stations and the users' mobility patterns, due to the classification reveals imbalances in the distribution of bikes and lead to a better understanding of the system structure. The proposed method is applied to the Dublin Bikes Scheme with good performance results.