Exploring the relationship between built environment and bike-sharing demand: Does the trip length matter?

TL;DR

This study investigates how the built environment influences bike-sharing demand differently based on trip length, using a novel threshold identification and a semiparametric geographically weighted Poisson regression model.

Contribution

It introduces a method to identify trip length thresholds and analyzes the heterogeneous effects of built environment on demand across different trip length groups.

Findings

Built environment effects vary across trip length groups.

A threshold for trip lengths was identified from data.

Heterogeneous impacts of built environment inform bike placement strategies.

Abstract

Bike-sharing has received considerable practice and research attention over the past decade. As a manpower-driven transportation mode, it seems more sensitive to trip length, since one could take a shared bike to a destinated place where is too far to walk, or choose it for simply replacing walking when going to a nearby place. However, little research has paid attention to it, i.e., the differentiated effects of built environment on the bike-sharing demand with trip lengths. To fill the gap, this paper identifies a threshold of bike-sharing trip lengths from bike-sharing trace data, and employs a semiparametric geographically weighted Poisson regression (SGWPR) model to investigate the relationship between built environment and bike-sharing demand with different lengths considering the heterogeneity in the relationship. The results show that built environment has heterogeneous effects on the bike-sharing demand in urban areas, and the effects differ across groups with trip lengths. The findings contribute to understanding the relationships between built environment and bike-sharing demand, and providing supports for the placements and dispatchment of shared bikes.