Abstract This research focuses on predicting the demand for air taxi urban air mobility (UAM) services during different times of the day in various geographic regions of New York City using machine learning algorithms (MLAs). Several ride-related factors (such as month of the year, day of the week and time of the day) and weather-related variables (such as temperature, weather conditions and visibility) are used as predictors for four popular MLAs, namely, logistic regression, artificial neural networks, random forests, and gradient boosting. Experimental results suggest gradient boosting to consistently provide higher prediction performance. Specific locations, certain time periods and weekdays consistently emerged as critical predictors.

    Highlights Air taxi is an emerging on-demand urban air mobility service for daily commute. Predicts customer demand level for air taxi service using machine learning algorithms. Considers both ride- and weather-related variables as predictors. Gradient boosting algorithm achieves best predictive performance. Identifies several critical predictors affecting the customer demand level.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Predicting demand for air taxi urban aviation services using machine learning algorithms


    Beteiligte:


    Erscheinungsdatum :

    2021-02-04




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Predicting Taxi-Passenger Demand Using Streaming Data

    Moreira-Matias, L | Online Contents | 2013


    Predicting Taxi–Passenger Demand Using Streaming Data

    Moreira-Matias, Luis / Gama, Joao / Ferreira, Michel et al. | IEEE | 2013



    Demand for taxi services: new elasticity evidence

    Rose, John M. / Hensher, David A. | Online Contents | 2013


    Demand for taxi services: new elasticity evidence

    Rose, John M. / Hensher, David A. | Online Contents | 2013