摘要
股票市场是金融分析领域中重要而困难的问题。股票数据的分析和预测具有重大的理论意义和诱人的应用价值。BP神经网络在目前的股票预测系统中应用广泛,但是作为有导师的学习系统,BP神经网络必须要求提供相关的经验数据才能正常运行。对此本文提出了一种基于强化学习BP算法应用于股票预测系统,通过强化学习体系来实现体统的自学习,通过网络集成来达到初始数据的预处理,提高系统的泛化能力,在实际应用中取的较好的效果。
The stock market is the most important and hard field of finance analysis field. The stock forecasting system is one of the most available system. BP neural network has been used in nonlinear system controller widely. But as a supervised training algorithm, it requires experiential data to be trained. So this paper provides the optimization on a reinforcement learning algorithm based on neural network ensemble and applies to a stock forecasting system . Reinforcement learning is unsupervised and on-line. Neural network ensemble can significantly improve the generalization ability of learning system. The method is tested and the expected results are obtained.
出处
《微计算机信息》
北大核心
2006年第02X期149-151,共3页
Control & Automation
基金
教育部留学回国基金2001498
关键词
股票预测
BP神经网络
强化学习
RBP模型
stock forecasting system, BP neural network, reinforcement learning, reinforcement back-propagation model