During the last few years, Bike Sharing Systems (BSS) have become a popular means of transportation in several cities across the world, owing to their low costs and associated advantages. Citizens have adopted these systems as they help improve their health and contribute to creating more sustainable cities. However, customer satisfaction and the willingness to use the systems are directly affected by the ease of access to the docking stations and finding available bikes or slots. Therefore, system operators and managers' major responsibilities focus on urban and transport planning by improving the rebalancing operations of their BSS. Many approaches can be considered to overcome the unbalanced station problem, but predicting the number of arrivals and departures at the docking stations has been proven to be one of the most efficient. In this paper, we study the features that influence the prediction of bikes' arrivals and departures in Barcelona BSS, using a Random Forest model and a one-year data period. We considered features related to the weather, the stations' characteristics, and the facilities available within a 200-meter diameter of each station, called spatial features. The results indicate that features related to specific months, as well as temperature, pressure, altitude, and holidays, have a strong influence on the model, while spatial features have a small impact on the prediction results.
Keywords: Bike Sharing Systems; Bike demand forecasting; Feature importance.
© 2024 The Authors.