Abstract In recent years, car-sharing services have emerged as viable alternatives to private individual mobility, promising more sustainable and resource-efficient, but still comfortable transportation. Research on short-term prediction and optimization methods has improved operations and fleet control of car-sharing services; however, long-term projections and spatial analysis are sparse in the literature. We propose to analyze the average monthly demand in a station-based car-sharing service with spatially-aware learning algorithms that offer high predictive performance as well as interpretability. Our study utilizes a rich set of socio-demographic, location-based (e.g., POIs), and car-sharing-specific features as input, extracted from a large proprietary car-sharing dataset and publicly available datasets. We first compare the performance of different modeling approaches and find that a global Random Forest with geo-coordinates as part of input features achieves the highest predictive performance with an R-squared score of 0.87 on test data. While a local linear model, Geographically Weighted Regression, performs almost on par in terms of out-of-sample prediction accuracy. We further leverage the models to identify spatial and socio-demographic drivers of car-sharing demand. An analysis of the Random Forest via SHAP values, as well as the coefficients of GWR and MGWR models, reveals that besides population density and the car-sharing supply, other spatial features such as surrounding POIs play a major role. In addition, MGWR yields exciting insights into the multiscale heterogeneous spatial distributions of factors influencing car-sharing behaviour. Together, our study offers insights for selecting effective and interpretable methods for diagnosing and planning the placement of car-sharing stations.

    Highlights Geographical analysis of long-term car sharing demand with spatially-explicit regression models Local and global models achieve high predictive performance when considering spatial features and sociodemographics Geographically Weighted Regression analysis and SHAP value analysis foster spatial interpretability Case study on utilizing the methods as a decision support system for car-sharing station planning


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Spatially-aware station based car-sharing demand prediction


    Beteiligte:


    Erscheinungsdatum :

    2023-11-28




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Station-Level Hourly Bike Demand Prediction for Dynamic Repositioning in Bike Sharing Systems

    Wu, Xinhua / Lyu, Cheng / Wang, Zewen et al. | Springer Verlag | 2019


    Prediction of Station Level Demand in a Bike Sharing System Using Recurrent Neural Networks

    Chen, Po-Chuan / Hsieh, He-Yen / Sigalingging, Xanno Kharis et al. | IEEE | 2017


    Modeling bike-sharing demand using a regression model with spatially varying coefficients

    Wang, Xudong / Cheng, Zhanhong / Trépanier, Martin et al. | Elsevier | 2021


    Performance Evaluation of Station-Based Autonomous On-Demand Car-Sharing Systems

    Javanshour, Farid / Dia, Hussein / Duncan, Gordon et al. | IEEE | 2022


    Demand Management of Station-Based Car Sharing System Based on Deep Learning Forecasting

    Daben Yu / Zongping Li / Qinglun Zhong et al. | DOAJ | 2020

    Freier Zugriff