A Dual-Attention-Based Stock Price Trend Prediction Model With Dual Features
A Dual-Attention-Based Stock Price Trend Prediction Model With Dual Features
复制标题
DOI：
10.1109/access.2019.2946223
复制
发表时间：
2019-01-01
期刊：
影响因子：
3.9
通讯作者：
Wang, James Z.
中科院分区：
文献类型：
--
作者：
Chen, Yingxuan;Lin, Weiwei;Wang, James Z.
股票价格的建模与预测是金融市场领域一个重要而又具有挑战性的课题。由于股票价格的高波动性，传统的数据挖掘方法无法识别出最相关和最关键的市场数据来预测股票价格的趋势。本文提出了一种基于编码器-解码器框架的股票价格趋势预测模型（TPM），该模型能够自适应地预测股票价格的变化及其持续时间。该模型包括两个阶段，首先，提出了一种基于不同时间跨度的双重特征提取方法，以从市场数据中获得更多的信息。传统的方法只能从特定时间点的信息中提取特征，而该模型应用PLR方法和CNN从市场数据中提取长期时间特征和短期空间特征。然后，在TPM的第二阶段，使用基于双重注意机制的编码器-解码器框架来选择和合并相关的双重特征并预测股票价格趋势。为了评估我们提出的TPM，我们收集了高频市场数据的股票指数CSI 300，上证50和CSI 500，并进行了实验的基础上，这三个数据集。实验结果表明，所提出的TPM优于现有的最先进的方法，包括SVR，LSTM，CNN，LSTM_CNN和TPM_NC，在预测精度方面。
Modeling and predicting stock prices is an important and challenging task in the field of financial market. Due to the high volatility of stock prices, traditional data mining methods cannot identify the most relevant and critical market data for predicting stock price trend. This paper proposes a stock price trend predictive model (TPM) based on an encoder-decoder framework that predicting the stock price movement and its duration adaptively. This model consists of two phases, first, a dual feature extraction method based on different time spans is proposed to get more information from the market data. While traditional methods only extract features from information at some specific time points, this proposed model applies the PLR method and CNN to extract the long-term temporal features and the short-term spatial features from market data. Then, in the second phase of the proposed TPM, a dual attention mechanism based encoder-decoder framework is used to select and merge relevant dual features and predict the stock price trend. To evaluate our proposed TPM, we collected high-frequency market data for stock indexes CSI300, SSE 50 and CSI 500, and conducted experiments based on these three data sets. The experimental results show that the proposed TPM outperforms the existing state-of-art methods, including SVR, LSTM, CNN, LSTM_CNN and TPM_NC, in terms of prediction accuracy.