基于深度学习的股票市场预测
首发时间:2014-02-24
摘要:股票市场在整个金融市场中起着很重要的作用。而股票价格波动的预测是最具有吸引力并且有意义的研究问题之一。股票价格预测的关键问题是如何设计一个方法可以提高预测的精度。已有的一些研究指出,传统的一些机器学习的方法都使用浅层的结构,如单隐层的神经网络和支持向量机。对于有限数量的样本和计算单元,浅层结构难以有效地表示复杂的函数,并且对于复杂分类问题表现性能及泛化能力均有明显的不足,尤其当目标函数具有丰富的含义。深度学习可以通过学习一种浅层非线性网络结构,实现复杂函数逼近,表征输入数据分布式表示,并体现了它对于输入样本数据的强大的本质特征的抽取能力。为了测试深度学习在股票价格预测问题上的性能,我们用港交所(HKEx)2001年的交易数据作为测试。实验结果表明,基于深度学习算法进行股票价格预测模型可以有较好的样本本质特征的抽取能力,能够反映样本的本质特征,并取得比较好的预测结果。
For information in English, please click here
The Stock Market Prediction via Deep Learning
Abstract:Stock market plays an important role in nowadays financial markets. And stock price volatility prediction is regarded as one of the most attractive and meaningful research issues. The key problem of the stock market prediction is how to design a method to improve the prediction accuracy. Some existing researches on stock market price volatility prediction have pointed out that architectures are applied in many existing machine learning algorithms including neural networks with only one hidden layer and support vector machine are using shallow architectures. Psychology results shows with limited samples and finite computing units, those shallow architectures are incapable of representing the complex function, and place restriction on the generalization capability of classifying complicated issues, especially for the rich sensory input. Deep learning achieves the approximation of complex function,characterization of the input data by learning a deep nonlinear network, and shows the great power in extracting the intrinsic feature of the training data. To validate the performance of Deep Learning, we take experiments on HKEx 2001 stock market datasets. The results show that deep learning has a the great power in extracting the intrinsic feature of the training data and it can refect the intrinsic feature of the training data.
Keywords: Deep Learning Stock Market Prediction Machine Learning Multi-Sourcedata Processing
论文图表:
引用
No.4585804955042139****
同行评议
勘误表
基于深度学习的股票市场预测
评论
全部评论0/1000