For forecasting closing price in stock market, we firstly divides samples which have characteristic of decentralization into different sub-classes with the aid of SOM neural network.

• 另一方面，由于预测因子之间的相关性，导致输入信息重叠，也使得模型预报的准确率降低，因此，应对此类样本和众多的预报因子进行必要的处理。