The emergence of online taxi-hailing fills the shortages of the taxi supply, but the reservable feature of online taxi-hailing has led to the increment of road parking, which has aggravated traffic congestion. Improving the prediction accuracy of online taxi-hailing demand is crucial to reducing congestion. Moreover, the traffic demand of different modes that influence each other is affected simultaneously by the environment, land-use characteristics, and geographic location. Therefore, we introduced a forecasting framework to improve online taxi-hailing demand forecasting accuracy based on multimode traffic in metro station areas and explored the best predictive range of metro station areas with different land-use characteristics. The paper extracted the origin and destination (OD) information from taxi, online taxi-hailing, and metro data. Next, we extracted the essential factors from the environmental data through Pearson’s coefficient analysis. Finally, we selected the best predictive model from several models that contain different information and explored the best predictive range. The result indicates that multisource traffic data and considering multimode traffic could improve traffic demand prediction accuracy. Furthermore, we found that the best traffic demand predictive ranges in metro station areas with different land-use characteristics are different.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Short-Term Online Taxi-Hailing Demand Prediction Based on the Multimode Traffic Data in Metro Station Areas


    Weitere Titelangaben:

    J. Transp. Eng., Part A: Systems


    Beteiligte:
    Liu, Zhizhen (Autor:in) / Chen, Hong (Autor:in)


    Erscheinungsdatum :

    2022-06-01




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    TAXI HAILING SYSTEM AND TAXI HAILING METHOD

    NAKAMURA KAZUTO | Europäisches Patentamt | 2019

    Freier Zugriff


    Prediction for Taxi-Hailing Demand—An Adaptive Multi-view Deep Learning Model

    Tang, Xin / Ma, Yongfeng / Xie, Zhuopeng et al. | Springer Verlag | 2022


    Prediction for Taxi-Hailing Demand—An Adaptive Multi-view Deep Learning Model

    Tang, Xin / Ma, Yongfeng / Xie, Zhuopeng et al. | TIBKAT | 2023


    Taxi Booking Mobile App Order Demand Prediction Based on Short-Term Traffic Forecasting

    Li, Yunxuan / Lu, Jian / Zhang, Lin et al. | Transportation Research Record | 2017