论文部分内容阅读
本文选取2009年1月5日～10月29日的大豆期货主力A1001合约共200个交易数据作为训练数据,10月30日～11月12日的10个数据为测试数据,利用BP神经网络对期货价格建立预测模型,并用遗传算法进行修正,从而实现对大豆期货交易价格的预测分析。结果表明,改进后的GA-BP神经网络模型拟合精度明显高于BP神经网络模型,并对期货价格走势有良好的预测效果,可给期货市场的投资者提供投资建议。此外,利用改进后的模型可对期货市场操纵现象进行预警,对监管者具有一定参考价值。
In this paper, a total of 200 transaction data of soybean futures contract A1001 from January 5 to October 29, 2009 were selected as training data and 10 data from October 30 to November 12 as test data. BP neural network Futures prices to establish a predictive model, and use genetic algorithms to amend, so as to achieve the forecast of soybean futures trading prices. The results show that the improved GA-BP neural network model fitting accuracy is significantly higher than the BP neural network model, and the futures price movements have a good predictive effect, to the investors in the futures market to provide investment advice. In addition, the improved model can be used to early warning on the manipulation of the futures market, which is of certain reference value for regulators.