The paper is aimed at commodity price forecasting using a numerical solution of the Cauchy initial problem for the 1st order ordinary differential equation. To acquire significant forecasting improvement, the idea of the modification of the initial condition value was realized. By having analysed the forecasting success of determined numerical models, it was found out that commodity price evolution affected the accuracy of the price forecasting. The absolute percentage prognoses errors were usually lower at a stable price increase and when price fluctuation appeared. Therefore, prognoses calculated without changing initial condition value were satisfying. Within significant changes in the price evolution and at a rapid price increase, the prognoses acquired higher absolute percentage errors. That caused replacing the initial condition value by the nearest stock exchange. Consider this strategy, the following calculated prognoses got closer to the forecast stock exchanges and price forecasting became more advantageous with respect to the price course.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    INFLUENCE OF THE PRICE MOVEMENTS TO THE ACCURACY WITHIN NUMERICAL PRICE FORECASTING


    Beteiligte:


    Erscheinungsdatum :

    2019




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Unbekannt