灰色Verhulst模型的灰导数改进研究

Pattern Mining on Financial Time Series Based on Extraction of Features

针对灰色Verhulst模型灰导数白化的问题,以白化微分方程为基础,运用梯形公式来白化灰导数,推导得到一种新的Verhulst模型定义式。该方法使得差分方程的参数与其在微分方程中对应的参数具有更好的一致性。实例分析表明改进的灰色Verhulst模型具有更高的预测和模拟精度。

As to the problem of whitening derivative item in grey Verhulst model, this paper presents a novel model, based on the white differential equation and trapezoid formula. The improved grey Verhulst model has eliminated some error of the traditional model, but also caused a better uniformity of parameters between the difference equation and differential equation in the grey model. The result indicates that the new modeling method proposed in this paper enhanced the grey derivative＇s accuracy as well as the model＇s precision of simulation and forecasting.