I just got done presenting at IJCAI09 on the shared bicycling research I conducted while a visiting researcher in the summer of 2008 at Telefonica Research in Barcelona, Spain. This is joint work with Joachim Neumann and Nuria Oliver (both of Telefonica Research). You can download the talk (PowerPoint slides) here.
Community shared bicycling programs offer an environmentally friendly, healthy, and inexpensive alternative to automobile transportation. Recent technological advances have led to a third generation shared bicycling system whose real-time usage data can be collected, archived, and analyzed. Currently, there are over forty such programs in the world including SmartBikeDC in Washington D.C. and Vélib’ in Paris, which has 20,000 bicycles and 1,450 stations (approximately 1 station every 300 meters). Barcelona’s shared bicycle program, Bicing, was launched in March of 2007. It currently has 390 stations with 6,000 bicycles and over 150,000 yearly subscribers.
Abstract
City-wide urban infrastructures are increasingly reliant on network technology to improve and ex-pand their services. As a side effect of this digitali-zation, large amounts of data can be sensed and analyzed to uncover patterns of human behavior. In this paper, we focus on the digital footprints from one type of emerging urban infrastructure: shared bicycling systems. We provide a spatiotemporal analysis of 13 weeks of bicycle station usage from Barcelona’s shared bicycling system, called Bicing. We apply clustering techniques to identify shared behaviors across stations and show how these behaviors relate to location, neighborhood, and time of day. We then compare experimental results from four predictive models of near-term station usage. Finally, we analyze the impact of factors such as time of day and station activity in the prediction capabilities of the algorithms.
Some pictures (with captions) from the talk:
Our focus was on utilizing existing urban infrastructure to sense data about human behavior that is *freely* available (e.g., not proprietary data but data that we can freely access). In this case, we use shared bicycling usage to uncover spatiotemporal patterns of human mobility in the city of Barcelona.
We have reached a pivotal point in time where city infrastructures are transitioning from mechanical/analog systems to digital systems thereby creating digital traces of human activity. Bruno Latour notes the potential to access the masses of data that are of the same order of magnitude as that of the natural sciences.
Our main contributions were: (1) demonstrating the potential of using shared bicycling as a data source to gain insights into city dynamics and aggregated human be-havior; (2) exploring the relationship between spatiotemporal patterns of bicycle usage and underlying city behavior and geography; and (3) studying patterns in bicycle station usage, including the prediction of usage patterns and an analysis of how factors such as the time of the day affect this prediction.
We obtained our data by scraping the bicing website once every two minutes. We downloaded station geolocation information as well as the number of current free parking spots and number of currently available bicycles.
One of our motivations to explore prediction was the fact that 66% respondents to an online survey about Bicing stated that they had difficulty finding a free parking slot when trying to drop off a bicycle. This is a major impediment to Barcelona residents adopting Bicing as a primary form of transportation as searching for a station with a free parking spot takes time. Indeed, 50% of respondents avoid Bicing when they are traveling to a place where they must be on time.
We used dendrogram clustering on station temporal usage data to see how Bicing usage patterns are shared across the city. We also explored how our prediction algorithms performed in relation to these clusters.
One longterm goal of our work is to explore ways to make shared bicycling more self-sustainable. Current shared bicycling systems rely on trucks to load balance the bicycles (i.e., to make sure they are well distributed throughout the city). We are looking at ways to incentivize bicing users to drop off/pick up bicycles slightly out of their way to reduce the maintenance/operating overhead on the city. A mobile phone application could recommend a station close to a user’s final destination that is predicted to have a need for bicycles.
This work would not have been possible without my colleagues Joachim Neumann and Nuria Oliver. Joachim, in particular, worked tirelessly on this project for six months and was absolutely essential to many parts of the project including data logging, model building, and evaluation.
[...] all potentially provide data that can be used to understand and model the city. We did a bit of this work on shared bicycling–i.e., what does shared bicycling data reveal about a city? Marcus Foth has a book called [...]