ST-Trader:A Spatial-Temporal Deep Neural Network for Modeling Stock Market Movement

作     者：Xiurui Hou Kai Wang Cheng Zhong Zhi Wei Xiurui Hou;Kai Wang;Cheng Zhong;Zhi Wei

作者机构：the Department of Computer ScienceNew Jersey Institute of TechnologyNewarkNJ 07102 USA the School of BusinessStevens Institute of TechnologyHobokenNJ 07030 USA 

出 版 物：《IEEE/CAA Journal of Automatica Sinica》 (自动化学报（英文版）)

年 卷 期：2021年第8卷第5期

页      面：1015-1024页

核心收录：

学科分类：0810[工学-信息与通信工程] 1205[管理学-图书情报与档案管理] 02[经济学] 0202[经济学-应用经济学] 08[工学] 081104[工学-模式识别与智能系统] 020202[经济学-区域经济学] 0802[工学-机械工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Graph convolution network long-short term memory network stock market forecasting variational autoencoder(VAE) 

摘      要：Stocks that are fundamentally connected with each other tend to move together.Considering such common trends is believed to benefit stock movement forecasting tasks.However,such signals are not trivial to model because the connections among stocks are not physically presented and need to be estimated from volatile data.Motivated by this observation,we propose a framework that incorporates the inter-connection of firms to forecast stock prices.To effectively utilize a large set of fundamental features,we further design a novel pipeline.First,we use variational autoencoder(VAE)to reduce the dimension of stock fundamental information and then cluster stocks into a graph structure(fundamentally clustering).Second,a hybrid model of graph convolutional network and long-short term memory network(GCN-LSTM)with an adjacency graph matrix(learnt from VAE)is proposed for graph-structured stock market forecasting.Experiments on minute-level U.S.stock market data demonstrate that our model effectively captures both spatial and temporal signals and achieves superior improvement over baseline methods.The proposed model is promising for other applications in which there is a possible but hidden spatial dependency to improve time-series prediction.