Stock movement prediction with market dynamic hierarchical macro information

doi:10.11772/j.issn.1001-9081.2022030400

Journal of Computer Applications ›› 2023, Vol. 43 ›› Issue (5): 1378-1384.DOI: 10.11772/j.issn.1001-9081.2022030400

• China Conference on Data Mining 2022 (CCDM 2022) • Previous Articles

Stock movement prediction with market dynamic hierarchical macro information

Yafei ZHANG¹^,²^,³, Jing WANG¹^,²^,³, Yaoshuai ZHAO³^,⁴(), Zhihao WU¹^,²^,³, Youfang LIN¹^,²^,³

^1.School of Computer and Information Technology，Beijing Jiaotong University，Beijing 100044，China
^2.Beijing Key Lab of Traffic Data Analysis and Mining （Beijing Jiaotong University），Beijing 100044，China
^3.Key Laboratory of Intelligent Application Technology for Civil Aviation Passenger Services，Civil Aviation Administration of China，Beijing 101318，China
^4.TravelSky Technology Limited，Beijing 101318，China

Received:2022-03-30 Revised:2022-05-17 Accepted:2022-05-26 Online:2023-05-08 Published:2023-05-10
Contact: Yaoshuai ZHAO
About author:ZHANG Yafei， born in 1997， M. S. candidate. His research interests include data mining， machine learning.
WANG Jing， born in 1987， Ph. D.， associate professor. Her research interests include time series analysis and mining.
ZHAO Yaoshuai， born in 1977， M. S.， senior engineer. His research interests include big data， artificial intelligence.
WU Zhihao， born in 1984， Ph. D.， associate professor. His research interests include social network analysis， data mining， machine learning
LIN Youfang， born in 1971， Ph. D.， professor. His research interests include intelligent system， complex network， traffic data mining.
Supported by:
Fund of TravelSky Technology Limited and Key Laboratory of Intelligent Application Technology for Civil Aviation Passenger Services(K20L00070)

融合市场动态层次宏观信息的股票趋势预测

张亚飞¹^,²^,³, 王晶¹^,²^,³, 赵耀帅³^,⁴(), 武志昊¹^,²^,³, 林友芳¹^,²^,³

^1.北京交通大学计算机与信息技术学院, 北京 100044
^2.交通数据分析与挖掘北京市重点实验室(北京交通大学), 北京 100044
^3.中国民用航空局民航旅客服务智能化应用技术重点实验室, 北京 101318
^4.中国民航信息网络股份有限公司, 北京 101318

通讯作者: 赵耀帅
作者简介:张亚飞（1997—），男，河北邢台人，硕士研究生，主要研究方向：数据挖掘、机器学习
王晶（1987—），女，安徽合肥人，副教授，博士，主要研究方向：时间序列分析与挖掘
赵耀帅（1977—），男，山东济宁人，高级工程师，硕士，主要研究方向：大数据、人工智能 yszhao@travelsky.com.cn
武志昊（1984—），男，山西大同人，副教授，博士，主要研究方向：社交网络分析、数据挖掘、机器学习
林友芳（1971—），男，福建武平人，教授，博士，主要研究方向：智能系统、复杂网络、交通数据挖掘。
基金资助:
中国民航信息网络股份有限公司和民航旅客服务智能化应用技术重点实验室基金资助项目(K20L00070)

Abstract

Abstract:

The complex structure and diverse imformation of stock markets make stock movement prediction extremely challenging. However， most of the existing studies treat each stock as an individual or use graph structures to model complex higher-order relationships in stock markets， without considering the hierarchy and dynamics among stocks， industries and markets. Aiming at the above problems， a Dynamic Macro Memory Network （DMMN） was proposed， and price movement prediction was performed for multiple stocks simultaneously based on DMMN. In this method， the market macro-environmental information was modeled by the hierarchies of “stock-industry-market”， and long-term dependences of this information on time series were captured. Then， the market macro-environmental information was integrated with stock micro-characteristic information dynamically to enhance the ability of each stock to perceive the overall state of the market and capture the interdependences among stocks， industries， and markets indirectly. Experimental results on the collected CSI300 dataset show that compared with stock prediction methods based on Attentive Long Short-Term Memory （ALSTM） network， GCN-LSTM （Graph Convolutional Network with Long Short-Term Memory）， Convolutional Neural Network （CNN） and other models， the DMMN-based method achieves better results in F1-score and Sharpe ratio， which are improved by 4.87% and 31.90% respectively compared with ALSTM， the best model among all comparison methods. This indicates that DMMN has better prediction performance and better practicability.

Key words: stock movement prediction, macro memory network, dynamic dependence, hierarchical macro information, gated unit

摘要：

股票市场结构复杂、信息多样，股票趋势预测极具挑战性。但现有研究大都把每只股票当作一个独立的个体，或者使用图结构对股票市场中复杂的高阶关系进行建模，缺少对股票、行业、市场三者间相互影响的层次性和动态性考量。针对上述问题，提出一种动态宏观记忆网络（DMMN），并基于DMMN同时对多只股票进行价格趋势预测。该方法按照“股票-行业-市场”的层次对市场宏观环境信息进行建模，并捕获这些信息在时序上的长期依赖；然后将市场宏观环境信息与股票微观特征信息动态融合，在增强个股对市场整体情况的感知能力的同时间接捕获到股票、行业、市场三者间的相互依赖。在收集的CSI300数据集上得到的实验结果表明，相较于基于注意力长短期记忆（ALSTM）网络、添加了图卷积的LSTM网络（GCN-LSTM）、卷积神经网络（CNN）等模型的股票预测方法，基于DMMN的方法在F1分数、夏普比率上都取得了更好的效果，和表现最优的对比方法ALSTM相比分别提升了4.87%和31.90%，这表明DMMN在具备较好预测性能的同时还具备更好的实用价值。

关键词: 股票趋势预测, 宏观记忆网络, 动态依赖, 层次宏观信息, 门控单元

CLC Number:

TP181

Yafei ZHANG, Jing WANG, Yaoshuai ZHAO, Zhihao WU, Youfang LIN. Stock movement prediction with market dynamic hierarchical macro information[J]. Journal of Computer Applications, 2023, 43(5): 1378-1384.

张亚飞, 王晶, 赵耀帅, 武志昊, 林友芳. 融合市场动态层次宏观信息的股票趋势预测[J]. 《计算机应用》唯一官方网站, 2023, 43(5): 1378-1384.

Figures/Tables 7

References 28

1	扈香梅. 浅谈基本面分析和技术分析在股票市场的应用［J］. 新西部（理论版）， 2014（8）： 62-62， 64. 10.3969/j.issn.1009-8607(z).2014.03.045
	HU X M. The application of fundamental analysis and technical analysis in the stock market［J］. New West， 2014（8）：62-62， 64. 10.3969/j.issn.1009-8607(z).2014.03.045
2	吴玉霞，温欣. 基于ARIMA模型的短期股票价格预测［J］. 统计与决策， 2016（23）： 83-86. 10.13546/j.cnki.tjyjc.2016.23.021
	WU Y X， WEN X. Short-term stock price forecast based on ARIMA model［J］. Statistics and Decision， 2016（23）： 83-86. 10.13546/j.cnki.tjyjc.2016.23.021
3	陈守东，俞世典. 基于GARCH模型的VaR方法对中国股市的分析［J］. 吉林大学社会科学学报， 2002（4）： 11-17.
	CHEN S D， YU S D. Analysis of China's stock market using VaR method based on GARCH model［J］. Jilin University Journal Social Sciences Edition， 2002（4）： 11-17.
4	HOU K W. Industry information diffusion and the lead-lag effect in stock returns［J］. The Review of Financial Studies， 2007， 20（4）： 1113-1138. 10.1093/revfin/hhm003
5	CHAN W S. Stock price reaction to news and no-news： drift and reversal after headlines［J］. Journal of Financial Economics， 2003， 70（2）： 223-260. 10.1016/s0304-405x(03)00146-6
6	孙华妤，马跃. 中国货币政策与股票市场的关系［J］. 经济研究， 2003（7）： 44-53， 91.
	SUN H S， MA Y. Monetary policy and stock market in China［J］. Economic Research Journal， 2003（7）： 44-53， 91.
7	WANG G F， CAO L B， ZHAO H K， et al. Coupling macro-sector-micro financial indicators for learning stock representations with less uncertainty［C］// Proceedings of the 35th AAAI Conference on Artificial Intelligence. Palo Alto， CA： AAAI Press， 2021： 4418-4426. 10.1609/aaai.v35i5.16568
8	DIEBOLD F X， YILMAZ K. On the network topology of variance decompositions： measuring the connectedness of financial firms［J］. Journal of Econometrics， 2014， 182（1）： 119-134. 10.1016/j.jeconom.2014.04.012
9	NOH J D. Model for correlations in stock markets［J］. Physical Review. E， Statistical Physics， Plasmas， Fluids， and Related Interdisciplinary Topics， 2000， 61（5）： 5981-5982. 10.1103/physreve.61.5981
10	刘文杰. 新冠肺炎疫情对互联网视频行业的影响［J］. 人文天下， 2020（10）： 10-14. 10.3969/j.issn.2095-3690.2020.10.003
	LIU W J. The impact of the COVID-19 on the Internet video industry［J］. Humanities in the World， 2020（10）： 10-14. 10.3969/j.issn.2095-3690.2020.10.003
11	夏杰长，丰晓旭. 新冠肺炎疫情对旅游业的冲击与对策［J］. 中国流通经济， 2020， 34（3）： 3-10. 10.14100/j.cnki.65-1039/g4.20200812.001
	XIA J C， FENG X X. The impact of the novel coronavirus outbreak on the tourism industry and its countermeasures［J］. China Business and Market， 2020， 34（3）： 3-10. 10.14100/j.cnki.65-1039/g4.20200812.001
12	XU Y M， COHEN S B. Stock movement prediction from tweets and historical prices［C］// Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics （Volume 1： Long Papers）. Stroudsburg， PA： ACL， 2018： 1970-1979. 10.18653/v1/p18-1183
13	FENG F L， CHEN H M， HE X N， et al. Enhancing stock movement prediction with adversarial training［C］// Proceedings of the 28th International Joint Conference on Artificial Intelligence. California： ijcai.org， 2019： 5843-5849. 10.24963/ijcai.2019/810
14	DING Q G， WU S F， SUN H， et al. Hierarchical multi-scale Gaussian transformer for stock movement prediction［C］// Proceedings of the 29th International Joint Conference on Artificial Intelligence. California： ijcai.org， 2020： 4640-4646. 10.24963/ijcai.2020/640
15	YE J X， ZHAO J J， YE K J， et al. Multi-graph convolutional network for relationship-driven stock movement prediction［C］// Proceedings of the 25th International Conference on Pattern Recognition. Piscataway： IEEE， 2021： 6702-6709. 10.1109/icpr48806.2021.9412695
16	SAWHNEY R， AGARWAL S， WADHWA A， et al. Spatiotemporal hypergraph convolution network for stock movement forecasting［C］// Proceedings of the 2020 IEEE International Conference on Data Mining. Piscataway： IEEE， 2020： 482-491. 10.1109/icdm50108.2020.00057
17	KODOGIANNIS V， LOLIS A. Forecasting financial time series using neural network and fuzzy system-based techniques［J］. Neural Computing and Applications， 2002， 11（2）： 90-102. 10.1007/s005210200021
18	JIANG W W. Applications of deep learning in stock market prediction： recent progress［J］. Expert Systems with Applications， 2021， 184： No.115537. 10.1016/j.eswa.2021.115537
19	HUYNH H D， DANG L M， DUONG D. A new model for stock price movements prediction using deep neural network［C］// Proceedings of the 8th International Symposium on Information and Communication Technology. New York： ACM， 2017： 57-62. 10.1145/3155133.3155202
20	NELSON D M Q， PEREIRA A C M， DE OLIVEIRA R A. Stock market's price movement prediction with LSTM neural networks［C］// Proceedings of the 2017 International Joint Conference on Neural Networks. Piscataway： IEEE， 2017： 1419-1426. 10.1109/ijcnn.2017.7966019
21	邓凤欣，王洪良. LSTM神经网络在股票价格趋势预测中的应用——基于美港股票市场个股数据的研究［J］. 金融经济， 2018（14）： 96-98.
	DENG F X， WANG H L. The application of LSTM neural network in stock price trend prediction - based on the research of individual stock data in the US and Hong Kong stock markets［J］. Finance Economy， 2018（14）：96-98.
22	HOCHREITER S， SCHMIDHUBER J. Long short-term memory［J］. Neural Computation， 1997， 9（8）： 1735-1780. 10.1162/neco.1997.9.8.1735
23	LI W， BAO R H， HARIMOTO K， et al. Modeling the stock relation with graph network for overnight stock movement prediction［C］// Proceedings of the 29th International Joint Conference on Artificial Intelligence. California： ijcai.org， 2020： 4541-4547. 10.24963/ijcai.2020/626
24	饶东宁，邓福栋，蒋志华. 基于多信息源的股价趋势预测［J］. 计算机科学， 2017， 44（10）： 193-202. 10.11896/j.issn.1002-137X.2017.10.036
	RAO D N， DENG F D， JIANG Z H. Stock price movement prediction based on multisources［J］. Computer Science， 2017， 44（10）： 193-202. 10.11896/j.issn.1002-137X.2017.10.036
25	张梦吉，杜婉钰，郑楠. 引入新闻短文本的个股走势预测模型［J］. 数据分析与知识发现， 2019， 3（5）： 11-18. 10.11925/infotech.2096-3467.2018.0871
	ZHANG M J， DU W Y， ZHENG N. Predicting stock trends based on news events［J］. Data Analysis and Knowledge Discovery， 2019， 3（5）： 11-18. 10.11925/infotech.2096-3467.2018.0871
26	KRYSOVATYY A， VASYLCHYSHYN O， DESYATNYUK O， et al. News feed for stock movement prediction［C］// Proceedings of the 15th International Conference on ICT in Education， Research and Industrial Applications， Volume I： Main Conference. Aachen： CEUR-WS.org， 2019： 90-97.
27	杨丽，吴雨茜，王俊丽，等. 循环神经网络研究综述［J］. 计算机应用， 2018， 38（S2）： 1-6， 26.
	YANG L， WU Y X， WANG J L， et al. Research on recurrent neural network［J］. Journal of Computer Applications， 2018， 38（S2）： 1-6， 26.
28	CHO K， van MERRIËNBOER B， GU̇LÇEHRE Ç， et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation［C］// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Stroudsburg， PA： ACL， 2014： 1724-1734. 10.3115/v1/d14-1179

数据段	开始日期	结束日期	股票数	行业数	样本数	l₁/%	l₂/%
1	2010-01-18	2011-09-07	177	65	70 800	-0.847 1	0.804 8
2	2012-01-30	2013-09-18	219	68	87 600	-0.746 4	0.727 3
3	2014-02-24	2015-10-13	231	69	92 400	-0.781 5	1.052 6
4	2016-03-10	2017-10-27	250	70	100 000	-0.521 1	0.517 6
5	2018-03-27	2019-11-15	272	73	108 800	-0.780 4	0.691 4

数据段	开始日期	结束日期	股票数	行业数	样本数	l₁/%	l₂/%
1	2010-01-18	2011-09-07	177	65	70 800	-0.847 1	0.804 8
2	2012-01-30	2013-09-18	219	68	87 600	-0.746 4	0.727 3
3	2014-02-24	2015-10-13	231	69	92 400	-0.781 5	1.052 6
4	2016-03-10	2017-10-27	250	70	100 000	-0.521 1	0.517 6
5	2018-03-27	2019-11-15	272	73	108 800	-0.780 4	0.691 4

数据段	F1分数							夏普比率
数据段	ARIMA	MLP	CNN	LSTM	GCN-LSTM	ALSTM	DMMN	ARIMA	MLP	CNN	LSTM	GCN-LSTM	ALSTM	DMMN
1	0.230 3	0.166 3	0.343 8	0.343 2	0.375 5	0.353 9	0.392 2	-0.005 2	-0.005 2	0.066 9	0.060 3	-0.045 3	0.057 2	0.066 3
2	0.213 8	0.171 6	0.284 8	0.365 6	0.346 3	0.366 7	0.409 2	-0.003 0	-0.003 0	0.008 8	0.041 2	-0.049 2	0.150 9	0.172 1
3	0.219 5	0.198 4	0.274 3	0.385 6	0.364 0	0.415 5	0.387 1	-0.002 5	-0.002 5	0.006 5	0.161 6	-0.007 3	0.171 1	0.195 5
4	0.242 4	0.163 2	0.389 4	0.384 3	0.362 0	0.382 7	0.395 6	0.096 2	-0.008 6	0.136 2	0.054 4	0.100 2	0.092 3	0.078 6
5	0.251 3	0.259 1	0.341 4	0.358 5	0.277 6	0.361 7	0.388 1	-0.007 0	-0.007 0	0.030 3	0.013 8	0.124 9	0.004 8	0.115 9
Ave	0.231 5	0.191 7	0.326 7	0.367 4	0.345 1	0.376 1	0.394 4	0.015 7	-0.005 3	0.049 7	0.066 3	0.024 7	0.095 3	0.125 7
Std	0.015 6	0.040 2	0.047 3	0.017 9	0.039 1	0.024 4	0.008 9	-0.005 2	-0.005 2	0.066 9	0.060 3	-0.045 3	0.057 2	0.066 3

数据段	F1分数							夏普比率
数据段	ARIMA	MLP	CNN	LSTM	GCN-LSTM	ALSTM	DMMN	ARIMA	MLP	CNN	LSTM	GCN-LSTM	ALSTM	DMMN
1	0.230 3	0.166 3	0.343 8	0.343 2	0.375 5	0.353 9	0.392 2	-0.005 2	-0.005 2	0.066 9	0.060 3	-0.045 3	0.057 2	0.066 3
2	0.213 8	0.171 6	0.284 8	0.365 6	0.346 3	0.366 7	0.409 2	-0.003 0	-0.003 0	0.008 8	0.041 2	-0.049 2	0.150 9	0.172 1
3	0.219 5	0.198 4	0.274 3	0.385 6	0.364 0	0.415 5	0.387 1	-0.002 5	-0.002 5	0.006 5	0.161 6	-0.007 3	0.171 1	0.195 5
4	0.242 4	0.163 2	0.389 4	0.384 3	0.362 0	0.382 7	0.395 6	0.096 2	-0.008 6	0.136 2	0.054 4	0.100 2	0.092 3	0.078 6
5	0.251 3	0.259 1	0.341 4	0.358 5	0.277 6	0.361 7	0.388 1	-0.007 0	-0.007 0	0.030 3	0.013 8	0.124 9	0.004 8	0.115 9
Ave	0.231 5	0.191 7	0.326 7	0.367 4	0.345 1	0.376 1	0.394 4	0.015 7	-0.005 3	0.049 7	0.066 3	0.024 7	0.095 3	0.125 7
Std	0.015 6	0.040 2	0.047 3	0.017 9	0.039 1	0.024 4	0.008 9	-0.005 2	-0.005 2	0.066 9	0.060 3	-0.045 3	0.057 2	0.066 3

数据段	MacroN	MMN	DMMN
1	0.354 3	0.362 3	0.392 2
2	0.373 1	0.373 2	0.409 2
3	0.385 8	0.399 5	0.387 1
4	0.405 4	0.402 6	0.395 6
5	0.370 0	0.362 5	0.388 1
Ave	0.377 7	0.380 0	0.394 4
Std	0.019 1	0.019 7	0.008 9

Stock movement prediction with market dynamic hierarchical macro information

融合市场动态层次宏观信息的股票趋势预测

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 7

References 28

Related Articles 15

Recommended Articles

Metrics

[1]	Zhirong HOU, Xiaodong FAN, Hua ZHANG, Xiaonan MA. J-SGPGN： paraphrase generation network based on joint learning of sequence and graph [J]. Journal of Computer Applications, 2023, 43(5): 1365-1371.
[2]	Yu TAN, Xiaoqin WANG, Rushi LAN, Zhenbing LIU, Xiaonan LUO. Multi-label cross-modal hashing retrieval based on discriminative matrix factorization [J]. Journal of Computer Applications, 2023, 43(5): 1349-1354.
[3]	Xinwei LYU, Shuxia LU. Iteratively modified robust extreme learning machine [J]. Journal of Computer Applications, 2023, 43(5): 1342-1348.
[4]	. Multiple clustering algorithm based on dynamic weighted tensor distance#br# #br# #br# [J]. Journal of Computer Applications, 0, (): 0-0.
[5]	. Spectral clustering based dynamic community discovery algorithm in social network [J]. Journal of Computer Applications, 0, (): 0-0.
[6]	. Collaborative filtering algorithm based on collaborative training and Boosting#br# #br# [J]. Journal of Computer Applications, 0, (): 0-0.
[7]	Yinjiang CAI, Guangjun XU, Xibo MA. Data enhancement method for drugs under graph-structured representation [J]. Journal of Computer Applications, 2023, 43(4): 1136-1141.
[8]	Jin XIA, Zhengqun WANG, Shiming ZHU. Traffic flow prediction model based on time series decomposition [J]. Journal of Computer Applications, 2023, 43(4): 1129-1135.
[9]	Nanfan LI, Wenwen SI, Siyuan DU, Zhiyong WANG, Chongyang ZHONG, Shihong XIA. Hidden state initialization method for recurrent neural network-based human motion model [J]. Journal of Computer Applications, 2023, 43(3): 723-727.
[10]	Mengting WANG, Wenzhong YANG, Yongzhi WU. Survey of single target tracking algorithms based on Siamese network [J]. Journal of Computer Applications, 2023, 43(3): 661-673.
[11]	Huayong YAO, Dongyi YE, Zhaojiong CHEN. Multi-round conversational reinforcement learning recommendation algorithm via multi-granularity feedback [J]. Journal of Computer Applications, 2023, 43(1): 15-21.
[12]	Sai ZHENG, Tianrui LI, Wei HUANG. Federated learning algorithm for communication cost optimization [J]. Journal of Computer Applications, 2023, 43(1): 1-7.
[13]	Yu LU, Lingyun ZHAO, Binwen BAI, Zhen JIANG. Imbalanced classification algorithm based on improved semi-supervised clustering [J]. Journal of Computer Applications, 2022, 42(12): 3750-3755.
[14]	Tiankai LIANG, Bi ZENG, Guang CHEN. Federated learning survey：concepts， technologies， applications and challenges [J]. Journal of Computer Applications, 2022, 42(12): 3651-3662.
[15]	Lingmin LI, Mengran HOU, Kun CHEN, Junmin LIU. Survey on interpretability research of deep learning [J]. Journal of Computer Applications, 2022, 42(12): 3639-3650.