Two-channel Attention Mechanism Fusion Model of Stock Price Prediction Based on CNN-LSTM

被引：20

作者：

Sun, Lin ^{[1
,2
]}

Xu, Wenzheng ^{[1
,2
]}

Liu, Jimin ^{[1
,2
]}

机构：

[1] Shandong Univ Sci & Technol, Coll Intelligent Equipment, Tai An, Shandong, Peoples R China

[2] 233 Daizong St, Tai An 271019, Shandong, Peoples R China

来源：

ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING | 2021年 / 20卷 / 05期

关键词：

CNN-LSTM; stock prediction; attention mechanism; two-channel; VOLATILITY; RETURNS;

D O I：

10.1145/3453693

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Using hierarchical CNN, the company's multiple news is characterized as three levels: sentence vectors, chapter vectors, and enterprise sentiment vectors. By combining the stock price data with the news lyric data at the same time, the influence of news on price is used to achieve correlation analysis of news information and stock prices. A two-channel attention mechanism fusion model based on CNN-LSTM is proposed. After the dual-channel feature extraction, the attention layer fusion layer is used to convert the weighted values of LSTM hidden variables, so the stock price can be predicted with the news text.

引用

页数：12

共 23 条

[1] Directional prediction of stock prices using breaking news on Twitter [J].

Alostad, Hana ;

Davulcu, Hasan .

Web Intelligence, 2017, 15 (01) :1-17

[2]

Bahdanau D, 2016, Arxiv, DOI arXiv:1409.0473

[3] GENERALIZED AUTOREGRESSIVE CONDITIONAL HETEROSKEDASTICITY [J].

BOLLERSLEV, T .

JOURNAL OF ECONOMETRICS, 1986, 31 (03) :307-327

[4]

Cai Shubin, 2018, P SMART COMP COMM 3

[5] The asymmetric reactions of mean and volatility of stock returns to domestic and international information based on a four-regime double-threshold GARCH model [J].

Chen, Cathy W. S. ;

Yang, Ming Jing ;

Gerlach, Richard ;

Lo, H. Jim .

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2006, 366 (01) :401-418

[6]

Cho K., 2014, P C EMP METH NAT LAN, P1724, DOI [10.3115/v1/D14-1179, DOI 10.3115/V1/D14-1179]

[7] AUTOREGRESSIVE CONDITIONAL HETEROSCEDASTICITY WITH ESTIMATES OF THE VARIANCE OF UNITED-KINGDOM INFLATION [J].

ENGLE, RF .

ECONOMETRICA, 1982, 50 (04) :987-1007

[8]

Gudelek MU, 2017, 2017 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (SSCI), P74

[9] A fuzzy GARCH model applied to stock market scenario using a genetic algorithm [J].

Hung, Jui-Chung .

EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (09) :11710-11717

[10]

Kaushal A, 2017, 2017 INTERNATIONAL CONFERENCE ON BIG DATA, IOT AND DATA SCIENCE (BID), P8, DOI 10.1109/BID.2017.8336565

← 1 2 3 →