Unlock a bike, unlock New York: A study of the New York citi bike system

Abstract

As urban populations grow, there is a growing need for efficient and sustainable modes, such as bicycling. The shortage of bicycle demand data is a barrier to design, planning, and research efforts in bicycle transportation before. In July 2013, the New York City implements the bike-sharing system, Citi Bike, and makes their data available for analysis. Data used in this study includes the information about active stations, average bicycles available, total annual membership, maintenance issues, events of vandalism and calls and emails to system center. Through statistic description, partial correlation analysis and principle component analysis, final variables are obtained. Finally, a Poisson regression model was adopted for the analysis. The analysis results are useful for understanding the influential factors including temperatures and weathers, which reflected by seasons generally, and supplements associated with rules or policy of bike-sharing system. In addition, the inferential results of these models provide guidance on future planning of station and bike supplement.