Prediction of Bike Share Demand by Machine Learning

In the fourth industrial revolution period, multinational companies and start-ups have applied a sharing economy concept to their business and have attempted to better serve customer demand by integrating demand prediction results into their business operations. For survival amongst today’s fierce competition, companies need to upgrade their prediction model to better predict customer demand in a more accurate manner. This study explores a new feature for bike share demand prediction models that resulted in an improved RMSLE score. By applying this new feature, the number of daily vehicle accidents reported in the Washington, D.C. area, to the Random Forest, XGBoost, and LightGBM models, the RMSLE score results improved. Many previous studies have primarily focused on feature engineering and regression techniques within given dataset. However, this study is meaningful because it focuses more on finding a new feature from an external data source.

If We Build It, Who Will Come? Comparing Sociodemographic Characteristics of Bike Share Subscribers, Cyclists, and Residents of New York City

Bike share programs are becoming increasingly popular across U.S. cities. However, their impact on persistent disparities in cycling by gender, race, and socioeconomic status remains understudied. We examined whether subscribers of Citi Bike, New York City’s (NYC) largest bike share program, reflect the sociodemographic profile of NYC cyclists. Using NYC Community Health Survey data, we described adult NYC residents of neighborhoods with ≥1 Citi Bike stations who rode a bicycle at least once a month. Citi Bike members were also described using first-time subscriber survey data. We compared the sociodemographic characteristics of these groups via a z-score with pooled variance. Approximately 2.2 million residents lived in 15 NYC neighborhoods with ≥1 Citi Bike station, and 449,000 (20.5%) reported cycling at least once a month in the past 12 months. Among first-time Citi Bike subscribers, 23,223 (11.5%) completed the survey. Compared with NYC cyclists, Citi Bike subscribers were more likely to be women, aged 24 to 45, White, college graduates, and from a household with an income >400% than the poverty level. Compared with the general population, cyclists were more likely to be White, male, and from a household with an income >400% than the poverty level. Race/ethnicity and socioeconomic status (not gender) disparities were larger among Citi Bike subscribers than NYC cyclists. With the emergence of cycling as an alternative transportation during the COVID-19 pandemic and the extension of bike share programs, this highlights the need for ongoing, systematic monitoring of bike share user socioeconomic characteristics to evaluate equitable use and access.

Changes in Urban Mobility Related to the Public Bike System with Regard to Weather Conditions and Statutory Retail Restrictions

The main purpose of the paper is to determine changes in transport behaviour of users of the public bike-share (PBS) scheme in a large Polish city, Łódź. By tracking GPS signals for individual trips taken by PBS users, it was possible to analyse their changeability (time and spatial) for periods before the implementation of statutory Sunday retail restrictions (2017) and after their partial introduction (2018). The study also took into account weather conditions, namely maximum and minimum daily temperatures and daily totals of precipitation recorded by a weather station in Łodź. In order to determine the correlations between certain weather conditions and PBS trips, the authors applied regression analysis. The results of the study showed that weekend cycling is less susceptible to the impact of weather than cycling on weekdays. At the same time, a comparative analysis of trading and non-trading Sundays proved that, during Sundays with retail restrictions, public bikes were used for longer, farther, and slower trips. These observations were confirmed by analyses of maps of traffic structure.