[Paper Review] Comparative Analysis of User Behavior of Dock-Based vs. Dockless Bikeshare and Scootershare in Washington, D.C

Kiana Roshan Zamir, Iryna Bondarenko+3 more|arXiv (Cornell University)|Jul 25, 2019

Urban Transport and Accessibility36 references4 citations

TL;DR

This study compares user behavior across dock-based bikeshare, dockless bikeshare, and dockless scootershare in Washington, D.C., using logistic regression and random forest models to classify trips as 'member' (commuter-like) or 'casual' (recreational). It finds that 63.8% of dockless bike and 69.6% of dockless scooter users exhibit member behavior—slightly below the 73.3% in dock-based systems—suggesting dockless systems support urban commuting and can enhance multi-modal infrastructure.

ABSTRACT

In 2017, dockless bikeshare systems were introduced in the United States, followed by dockless scootershare in early 2018. These new mobility options are expected to complement the existing station-based bikeshare systems, which are bound to static origin and destination points at docking stations. The three systems attract different users with different travel behavior mobility patterns. The present research provides a comparative analysis of users' behavior for these three shared mobility systems during March-May 2018 in the District of Columbia. Our study identifies similarities/differences between the two systems aiming for better planning, operating, and decision-making of these emerging personal shared mobility systems in the future. It uses logistic regression and random forest modeling to delineate between "member" behavior, which aligns most closely with commuter behavior, and "casual" behavior that represents more recreational behavior. The results show that 63.8% of dockless bike users and 69.6% of dockless scooter users demonstrated "member" behavior, which is slightly lower than the actual percentage of trips made by members within the conventional bikeshare system (73.3%). Dockless systems users also showed to have short trip durations similar to conventional bikeshare system's registered members, with no significant difference between trips during weekdays and weekends. Overall, this study provides a methodology to understand users' behavior for the dockless bikeshare system and provides sufficient evidence that these new shared mobility systems can potentially make positive contributions to urban multi-modal infrastructure by promoting bicycle usage for urban daily travel.

Motivation & Objective

• To understand and compare user behavior patterns across dock-based, dockless bikeshare, and dockless scootershare systems in Washington, D.C.
• To identify differences in trip characteristics, such as duration, timing, and user classification, between systems.
• To assess whether dockless systems attract users with commuter-like behavior, similar to traditional bikeshare members.
• To develop a methodology for classifying user behavior using statistical and machine learning models.
• To inform urban planning and policy decisions for integrating shared mobility systems into multi-modal infrastructure.

Proposed method

• Logistic regression and random forest modeling were used to classify user trips as 'member' (commuter-like) or 'casual' (recreational) behavior.
• Data from March to May 2018 was used, covering trips from dock-based bikeshare, dockless bikeshare, and dockless scootershare systems in D.C.
• Trip duration, day of week, and user type were key predictors in the classification models.
• The models were trained and validated on real-world mobility data to distinguish behavioral patterns across systems.
• User behavior was analyzed by comparing proportions of member vs. casual trips across the three systems.
• Statistical comparisons were made between weekday and weekend trip patterns for each system.

Experimental results

Research questions

• RQ1 How do user behavior patterns differ between dock-based bikeshare, dockless bikeshare, and dockless scootershare systems in Washington, D.C.?
• RQ2 To what extent do users of dockless systems exhibit 'member' behavior, indicative of commuting, compared to dock-based bikeshare users?
• RQ3 Are trip durations and timing (weekday vs. weekend) significantly different between dockless and dock-based systems?
• RQ4 What proportion of dockless bikeshare and scootershare trips are classified as 'member' behavior, and how do they compare to the dock-based system?
• RQ5 Can machine learning models effectively classify user behavior in emerging shared mobility systems based on trip data?

Key findings

• 63.8% of dockless bikeshare users and 69.6% of dockless scootershare users exhibited 'member' behavior, indicating a strong commuter-like user base.
• This proportion is slightly lower than the 73.3% of trips classified as 'member' behavior in the conventional dock-based bikeshare system.
• Dockless systems showed similar average trip durations to dock-based bikeshare, with no significant difference between weekday and weekend trips.
• The study confirms that dockless systems attract users with commuting patterns, supporting their integration into urban multi-modal networks.
• The application of logistic regression and random forest models successfully distinguished between commuter and recreational user behavior in shared mobility systems.
• The findings suggest dockless bikeshare and scootershare can contribute positively to urban transportation infrastructure by promoting daily bicycle use.