This paper introduces an approach to telematics device data application in automotive insurance. We conduct a comparative analysis of different types of devices that collect information on vehicle utilization and driving style of its driver and describe advantages and disadvantages of these devices. The possible formats of telematics data are described and methods of their processing to a format convenient for modeling are proposed. We also introduce an approach to classify the accidents’ strength. Using all the available information, we estimate accident probability models for different types of accidents and identify an optimal set of factors for each of the models. We assess the quality of resulting models using both in-sample and out-of-sample estimates.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Usage-based vehicle insurance: Driving style factors of accident probability and severity


    Beteiligte:

    Erschienen in:

    Erscheinungsdatum :

    06.10.2022


    Format / Umfang :

    22 pages




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Unbekannt




    Police Accident Report Restraint Usage Accuracy and Injury Severity

    Corrigan, Catherine / Raasch, Christine / Ray, Rose et al. | SAE Technical Papers | 2009


    AUTONOMOUS VEHICLE INSURANCE BASED UPON USAGE

    FIELDS BRIAN MARK / HUANG CHIEN CHE / WAZEER MOHAMED A et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Autonomous vehicle insurance based upon usage

    FIELDS BRIAN MARK / HUANG CHIEN CHE / WAZEER MOHAMED A et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Accident severity estimator for a vehicle

    CASTELLANO JAVIER | Europäisches Patentamt | 2016

    Freier Zugriff

    Predicting Vehicle Occupancies from Accident Data: An Accident Severity Approach

    Chang, Li-Yen / Mannering, Fred L. | Transportation Research Record | 1998