Based on the random forest model, this paper proposes a flight delay prediction model. By analyzing the departure flight data of Guangzhou Baiyun International Airport in June 2020, and selecting the data of ten landing airports, it analyzes the distribution of delayed, punctual, and early arrived. It studies the selection of features that impact on flight delays, and establishes random forest predictions model. Through case study, it researches the mean square error of different leaf sizes when the forest scale is 50 trees. The results show that the optimal leaf size is 5, and the minimum mean square error is 0.1096. And it analyzes the importance of features such as departure flight delay time, scheduled flight time, number of scheduled departure flights on the day, date, and landing airport. The research results also found that, when the forest size is 100 trees and the leaf size is 5, the out-of-bag mean square error is 0.1090, and the accuracy of the prediction model is high, which is close to 90%.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Research on Flight Delay Prediction Based on Random Forest


    Beteiligte:
    Hu, Peng (Autor:in) / Zhang, Jianping (Autor:in) / Li, Ning (Autor:in)


    Erscheinungsdatum :

    2021-10-20


    Format / Umfang :

    1048509 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Flight Delay Prediction

    Martinez, Vincent | TIBKAT | 2012


    Flight delay prediction based on ARIMA

    Wang, Jingkai / Pan, Weijun | IEEE | 2022


    Flight delay prediction based on LightGBM

    Tao, Jiang / Man, Hua / Yanling, Li | IEEE | 2021


    Research on Flight Delay Propagation Prediction Method Based on Transformer

    Qu, Jingyi / Zhang, Lin / Wu, Shixing | IEEE | 2023


    Research on flight arrival delay prediction based on support vector machine

    Hu, Peng / Hou, Jia / Zhang, Jianping et al. | IEEE | 2022