摘要
现阶段,通过运用一系列的统计指标和科学方法对商品流通规模进行预警研究,并通过预警系统及时预报警情,为有关部门实施有效调控提供参考,已经成为国民经济持续、稳定和协调发展的必要条件之一。由于影响商品流通规模预警指标的因素具有多样性和复杂性的特点,通过神经网络的方法能较好地描述各个预警指标之间的关系而不需要确定的函数形式,从而可以克服许多传统的经济预警方法对非线性数据的拟合和预测的准确度不高的问题,因此,可以将BP神经网络方法引入商品流通规模预警研究中。
At present, one of the preconditions for the coordinated, stable and sustained development of national economy is to timely forecast the scale of commodity circulation with a series of statistics index and scientific methods. Due to the complex and multiple factors affecting the early-warning of commodity circulation scale, it is necessary to use neural network to describe the relations between the various index without confirmed functions and the network can avoid the fitting of the nonlinear data by traditional economic early-warning methods and the inaccurate forecasting. Therefore, it is feasible to introduce BP neural network into the early-warning of commodity circulation scale.
出处
《河北经贸大学学报》
北大核心
2009年第4期19-23,共5页
Journal of Hebei University of Economics and Business
关键词
商品流通规模
BP神经网络
经济预警
commodity circulation scale
BP neural network
economic early-warning