【摘要】 采用基于 T-S模型的模糊神经网络 ,用改进的遗传算法来训练网络权值 ,隶属函数参数调整算法则采用动量法和学习率自适应调整相结合的策略 ,以上证指数和厦新电子 (个股 )为研究对象予以建模和预测 .结果表明 ,此种模型具有较好的泛化、学习、映射能力 ,对股票市场或类似的非线性经济系统的走势研判或其相应预测决策具有较好的应用价值更多还原

【Abstract】 This paper presents a method for stock market modeling and forecasting via fuzzy neural network based on T\|S model, in which the improved genetic algorithm is used to train the connection weights of the fuzzy neural network , the algorithms of momentum and self-adaptive learning rate are used to learn membership parameters. It has been shown by the modeling and forecasting results about Shanghai stock market price index and Xiaxin electron price (a company stock price)that the method has reinforcement learning properties, mapping capabilities, reflecting ability. With respect to modeling and forecasting or relative decision of stock market or some other similar nonlinear economic system ,the method is available.更多还原