计算机工程与应用2024，Vol.60Issue(4)：192-199,8.DOI:10.3778/j.issn.1002-8331.2210-0050
融合图卷积和卷积自注意力的股票预测方法
Stock Prediction Method Combining Graph Convolution and Convolution Self-Attention
摘要
Abstract
With the continuous development of China's stock market,the trend of a stock is often affected by the devel-opment of the upstream and downstream industries of its enterprises.In view of the fact that the mainstream stock pre-diction model ignores the shortcomings of the correlation relationship between stocks,a stock trend prediction model fusing graph convolution and long convolution self-attention is proposed.Firstly,the relationship matrix of multiple associated stocks is calculated using the correlation coefficient,then the graph convolutional network combining rela-tionship matrix is used to extract the feature of the associated stocks.Secondly,the multi-head convolution is used to extract long-term features from attention.Finally,the classification loss function polynomial expansion framework is used to make trend prediction for loss function optimization.Experimental results show that the proposed model is superior to gated loop unit,time convolutional network and other models in terms of accuracy,precision,recall and F1 score.关键词
股票趋势预测/卷积自注意力/去趋势互相关系数Key words
stock trend forecasting/convolution self-attention/detrend the number of interrelationships分类
信息技术与安全科学引用本文复制引用
田红丽,崔姚,闫会强..融合图卷积和卷积自注意力的股票预测方法[J].计算机工程与应用,2024,60(4):192-199,8.基金项目
国家社会科学基金(19BGL054). （19BGL054）
