Exploring the determinants of bike-sharing member trips with explainable machine learning: insights from Chicago’s Divvy system

Abstract

Bike-sharing offers an eco-friendly and efficient transportation alternative, addressing traffic congestion, environmental concerns, and promoting healthier lifestyles. Understanding the factors that influence bike-sharing trips made by members is essential for the long-term operational and financial sustainability of bike-sharing systems. However, existing studies have primarily relied on survey data and traditional statistical models, which are often constrained by limited sample sizes and an inability to fully capture non-linear relationships or complex interactions between various factors and bike-sharing membership trips. To address these shortcomings, this study leverages million-level trip records from Chicago’s Divvy bike-sharing system and applies explainable machine learning model to identify key determinants influencing bike-sharing trips made by members. Unlike traditional survey-based studies, the proposed framework exploits large-scale operational data to capture complex behavioral patterns and interactions that are not readily observable using standard models. The results indicate a strong positive association between membership-based bike-sharing trips and weekday morning and afternoon commuting periods. Additional factors, such as longer travel distances, proximity to downtown, higher proportions of younger populations, and greater shares of non-White residents, are also positively associated with membership trip activity. These findings both corroborate and extend existing literature, while providing new, data-driven insights enabled by advanced analytical methods. Based on the identified determinants, the study proposes targeted policy and operational strategies to encourage bike-sharing membership adoption. By explicitly overcoming prior methodological limitations, this research offers a robust and scalable analytical framework to support bike-sharing operators in service planning, membership expansion, and the sustainable growth of urban mobility systems.

Keywords

Bike-sharing / Explainable machine learning / Micromobility / Shared mobility / Commuting patterns

References

[1] Adadi A, Berrada M. Peeking inside the black-box: A survey on explainable artificial intelligence (XAI). IEEE Access, 2018, 6: 52138-52160

[2] Albuquerque V, Sales Dias M, Bacao F. Machine learning approaches to bike-sharing systems: A systematic literature review. ISPRS International Journal of Geo-Information, 2021, 10(2): 62https://bluebikes.com/system-data

[3] Buck D, Buehler R, Happ P, Rawls B, Chung P, Borecki N. Are bikeshare users different from regular cyclists? A first look at short-term users, annual members, and area cyclists in the Washington, DC, region. Transportation Research Record, 2013, 2387(1): 112-119

[4] Chen C, Ma J, Susilo Y, Liu Y, Wang M. The promises of big data and small data for travel behavior (aka human mobility) analysis. Transportation Research Part c, Emerging Technologies, 2016, 68: 285-299

[5] Christoph, M. (2020). Interpretable machine learning: A guide for making black box models explainable.

[6] Divvy. (2023). Divvy Bicycle Stations. https://data.cityofchicago.org/Transportation/Divvy-Bicycle-Stations/bbyy-e7gq/about_data.

[7] Divvy Bikes. (2023) Divvybikes.com, https://divvybikes.com/.

[8] Eren E, Uz VE. A review on bike-sharing: The factors affecting bike-sharing demand. Sustainable Cities and Society, 2020, 54 101882

[9] Faghih-Imani, A., & Eluru, N. (2016). Incorporating the impact of spatio-temporal interactions on bicycle sharing system demand: A case study of New York CitiBike system. Journal of Transport Geography, 54, 218–227.

[10] Fishman E, Washington S, Haworth N. Barriers and facilitators to public bicycle scheme use: A qualitative approach. Transportation Research Part f, Traffic Psychology and Behaviour, 2012, 15(6): 686-698

[11] Fishman E, Washington S, Haworth N. Bike-sharing’s impact on car use: Evidence from the United States, Great Britain, and Australia. Transportation Research Part d, Transport and Environment, 2014, 31: 13-20

[12] Fishman E, Washington S, Haworth N, Watson A. Factors influencing bike-sharing membership: An analysis of Melbourne and Brisbane. Transportation Research Part A, Policy and Practice, 2015, 71: 17-30

[13] Guo Y, Yang L, Lu Y, Zhao R. Dockless bike-sharing as a feeder mode of metro commute? The role of the feeder-related built environment: Analytical framework and empirical evidence. Sustainable Cities and Society, 2021, 65 102594

[14] Kaviti S, Venigalla MM, Lucas K. Travel behavior and price preferences of bikesharing members and casual users: A Capital Bikeshare perspective. Travel Behaviour and Society, 2019, 15: 133-145

[15] Li Z. Leveraging explainable artificial intelligence and big trip data to understand factors influencing willingness to ridesharing. Travel Behaviour and Society, 2023, 31: 284-294

[16] Litan H, Rong K, Wu Y, Xie D, Zhang H, Zhao D. Profit versus sustainability in bikeshare. Sustainable Cities and Society, 2023, 93 104512

[17] Ma X, Yuan Y, Van Oort N, Hoogendoorn S. Bike-sharing systems’ impact on modal shift: A case study in Delft, the Netherlands. Journal of Cleaner Production, 2020, 259 120846

[18] Mangrio AG, Asif M, Ahmed E, Sabir MW, Khan T, Jahangir I. Hydraulic performance evaluation of pressure compensating (pc) emitters and micro-tubing for drip irrigation system. Science Technology and Development, Islamabad, 2013, 32(4): 290-298

[19] Molnar, C. (2020). Interpretable Machine Learning. Lulu. com.

[20] Morton C. The demand for cycle sharing: Examining the links between weather conditions, air quality levels, and cycling demand for regular and casual users. Journal of Transport Geography, 2020, 88 102854

[21] NACTO. (2023). Shared Micromobility Report: 2023. https://nacto.org/publication/shared-micromobility-report-2023/.

[22] NOAA. (2023) “Datasets | Climate Data Online (CDO) | National Climatic Data Center (NCDC).” https://www.ncdc.noaa.gov/cdo-web/datasets.

[23] Ogilvie, F., & Goodman, A. (2012). Inequalities in usage of a public bicycle sharing scheme: Socio-demographic predictors of uptake and usage of the London (UK) cycle hire scheme. Preventive Medicine, 55(1), 40–45.

[24] Olsen LH, Glad IK, Jullum M, Aas K. Using Shapley values and variational autoencoders to explain predictive models with dependent mixed features. Journal of Machine Learning Research, 2022, 23(213): 1-51

[25] Raux C, Zoubir A, Geyik M. Who are bike-sharing schemes members and do they travel differently? The case of Lyon’s “Velo’v” scheme. Transportation Research Part a, Policy and Practice, 2017, 106: 350-363

[26] Sariyer G, Mangla SK, Sozen ME, Li G, Kazancoglu Y. Leveraging explainable artificial intelligence in understanding public transportation usage rates for sustainable development. Omega, 2024, 127 103105

[27] Shah KJ, Pan SY, Lee I, Kim H, You Z, Zheng JM, Chiang PC. Green transportation for sustainability: Review of current barriers, strategies, and innovative technologies. Journal of Cleaner Production, 2021, 326 129392

[28] Shaheen SA, Zhang H, Martin E, Guzman S. China's Hangzhou public bicycle: Understanding early adoption and behavioral response to bikesharing. Transportation Research Record, 2011, 2247(1): 33-41

[29] Shaheen S, Guzman S. Worldwide bikesharing. Access Magazine, 2011, 1(39): 22-27

[30] Shaheen, S., Guzman, S., & Zhang, H. (2012). Bikesharing across the globe. City cycling, 183.

[31] Shapley, L. S. (1953). A value for n-person games. Classics in Game Theory, 69–79.

[32] Sun S, Wang Z, Wang W. Dockless or docked: Which bike-sharing mode is more environmentally friendly for the city? Current evidence from China's major cities. Cities, 2024, 147 104816System Data | Capital Bikeshare. Capitalbikeshare.com

[33] U.S. Census Bureau. (2023). American Community Survey 5-year estimates (2018–2023). https://data.census.gov/.

[34] U.S. Environmental Protection Agency. (2021). Smart Location Database (Version 3.0). https://www.epa.gov/smartgrowth/smart-location-database.

[35] Wang J, Lindsey G. Do new bike-sharing stations increase member use: A quasi-experimental study. Transportation Research Part a: Policy and Practice, 2019, 121: 1-11

[36] Wang K, Yan X, Zhu Z, Chen XM. Understanding bike-sharing usage patterns of members and casual users: A case study in New York City. Travel Behaviour and Society, 2024, 36 100793

[37] Wang X, Lindsey G, Schoner JE, Harrison A. Modeling bike-sharing station activity: Effects of nearby businesses and jobs on trips to and from stations. Journal of Urban Planning and Development, 2016, 142(1): 04015001

[38] Wang ZHE, Wu C, Zheng K, Niu X, Wang X. SMOTETomek-based resampling for personality recognition. IEEE Access, 2019, 7: 129678-129689

[39] Winters M, Hosford K, Javaheri S. Who are the ‘super-users’ of public bike-sharing? An analysis of public bike-sharing members in Vancouver, BC. Preventive Medicine Reports, 2019, 15 100946

[40] Wu C, Kim I. Analyzing the structural properties of bike-sharing networks: Evidence from the United States, Canada, and China. Transportation Research Part a: Policy and Practice, 2020, 140: 52-71

[41] Xu Y, Yan X, Liu X, Zhao X. Identifying key factors associated with ridesplitting adoption rate and modeling their nonlinear relationships. Transportation Research Part a: Policy and Practice, 2021, 144: 170-188

[42] Yin G, Huang Z, Fu C, Ren S, Bao Y, Ma X. Examining active travel behavior through explainable machine learning: Insights from Beijing, China. Transportation Research Part d: Transport and Environment, 2024, 127 104038

[43] Zanotto, M. (2014). Facilitators and barriers to public bike-sharing adoption and success in a city with compulsory helmet legislation: A mixed-methods approach. Simon Fraser University. Master of Science Thesis. https://summit.sfu.ca/item/14458.

[44] Zhang L, Zhang J, Duan ZY, Bryde D. Sustainable bike-sharing systems: Characteristics and commonalities across cases in urban China. Journal of Cleaner Production, 2015, 97: 124-133

[45] Zhu L, Ali M, Macioszek E, Aghaabbasi M, Jan A. Approaching sustainable bike-sharing development: A systematic review of the influence of built environment features on bike-sharing ridership. Sustainability, 2022, 14(10): 5795

Funding

Directorate for Engineering(2400153)

RIGHTS & PERMISSIONS

The Author(s)