Stock market volatility prediction method based on improved genetic algorithm and graph neural network

doi:10.11772/j.issn.1001-9081.2021030519

Journal of Computer Applications ›› 2022, Vol. 42 ›› Issue (5): 1624-1633.DOI: 10.11772/j.issn.1001-9081.2021030519

• Frontier and comprehensive applications • Previous Articles Next Articles

Stock market volatility prediction method based on improved genetic algorithm and graph neural network

Xiaohan LI(), Huading JIA, Xue CHENG, Taiyong LI

School of Economic Information Engineering，Southwestern University of Finance and Economics，Chengdu Sichuan 611130，China

Received:2021-04-06 Revised:2021-07-15 Accepted:2021-07-15 Online:2022-06-11 Published:2022-05-10
Contact: Xiaohan LI
About author:LI Xiaohan， born in 1985，Ph. D. candidate. His research interestsinclude financial information management，intelligent decision-making，big data，business intelligence.
JIA Huading， born in 1956，Ph. D.，professor. His researchinterests include machine learning，algorithmic trading，spread spectrum sequence design.
CHENG Xue， born in 1997， M. S. candidate. Her researchinterests include machine learning，quantitative trading.
LI Taiyong， born in 1979， Ph. D.， professor. His researchinterests include machine learning， pattern recognition， naturalcomputing.
Supported by:
Fundamental Research Funds for Central Universities(JBK2102001)

基于改进遗传算法和图神经网络的股市波动预测方法

李晓寒(), 贾华丁, 程雪, 李太勇

西南财经大学经济信息工程学院，成都 611130

通讯作者: 李晓寒
作者简介:李晓寒（1985—），男，山东济南人，博士研究生，CCF会员，主要研究方向：金融信息管理、智能决策、大数据、商务智能 lixiaohan134@163.com
贾华丁（1956—），男，四川成都人，教授，博士，CCF会员，主要研究方向：机器学习、算法交易、扩频序列设计
程雪（1997—），女，山西河津人，硕士研究生，CCF会员，主要研究方向：机器学习、量化交易
李太勇（1979—），男，四川安岳人，教授，博士，CCF高级会员，主要研究方向：机器学习、模式识别、自然计算。
基金资助:
中央高校基本科研业务费专项资金资助项目(JBK2102001)

Abstract

Abstract:

Aiming at the difficulty in selecting stock valuation features and the lack of time series relational dimension features during the prediction of stock market volatility by intelligent algorithms such as Support Vector Machine （SVM） and Long Short-Term Memory （LSTM） network， in order to accurately predict stock volatility and effectively prevent financial market risks， a new stock market volatility prediction method based on Improved Genetic Algorithm （IGA） and Graph Neural Network （GNN） named IGA-GNN was proposed. Firstly， the data of stock market trading index graph was constructed based on the time series relation between adjacent trading days. Secondly， the characteristics of evaluation indexes were used to improve Genetic Algorithm （GA） by optimizing crossover and mutation probabilities， thereby realizing the node feature selection. Then， the weight matrix of edge and node features of graph data was established. Finally， the GNN was used for the aggregation and classification of graph data nodes， and the stock market volatility prediction was realized. In the experiment stage， the studied number of total evaluation indexes of stock was 130， and 87 effective evaluation indexes were extracted from the above by IGA under GNN method， making the number of stock evaluation indexes reduced by 33.08%. The proposed IGA was applied to the intelligent algorithms for feature extraction. The obtained algorithms has the overall prediction accuracy improved by 7.38 percentage points compared with the intelligent algorithms without feature extraction. Compared with applying the traditional GA for feature extraction of the intelligent algorithms， applying the proposed IGA for feature extraction of the intelligent algorithms has the total training time shortened by 17.97%. Among them， the prediction accuracy of IGA-GNN method is the highest， which is 19.62 percentage points higher than that of GNN method without feature extraction. Compared with the GNN method applying the traditional GA for feature extraction， the IGA-GNN method has the training time shortened by 15.97% on average. Experimental results show that， the proposed method can effectively extract stock features and has good prediction effect.

Key words: stock market prediction, Genetic Algorithm (GA), Graph Neural Network (GNN), machine learning, feature selection

摘要：

针对支持向量机（SVM）、长短期记忆（LSTM）网络等智能算法在股市波动预测过程中股票评价特征选择困难及时序关系维度特征缺失的问题，为能够准确预测股票波动、有效防范金融市场风险，提出了一种基于改进遗传算法（IGA）和图神经网络（GNN）的股市波动预测方法——IGA-GNN。首先，利用相邻交易日间的时序关系构建股市交易指标图数据；其次，通过评价指标特性优化交叉、变异概率来改进遗传算法（GA），从而实现节点特征选择；然后，建立图数据的边与节点特征的权重矩阵；最后，运用GNN进行图数据节点的聚合与分类，实现了股市波动预测。在实验阶段，所研究的股票总评价指标数为130个，其中IGA在GNN方法下提取的有效评价指标87个，使指标数量降低了33.08%。应用所提IGA在智能算法中进行特征提取，得到的算法与未进行特征提取的智能算法相比，预测准确率整体提升了7.38个百分点；而与应用传统GA进行智能算法的特征提取相比，应用所提IGA进行智能算法的特征提取的总训练时间缩短了17.97%。其中，IGA-GNN方法的预测准确率最高，相较未进行特征提取的GNN方法的预测准确率整体提高了19.62个百分点；而该方法与用传统GA进行特征提取的GNN方法相比，训练时间平均缩短了15.97%。实验结果表明，所提方法可对股票特征进行有效提取，预测效果较好。

关键词: 股市预测, 遗传算法, 图神经网络, 机器学习, 特征选择

CLC Number:

TP391.7

Xiaohan LI, Huading JIA, Xue CHENG, Taiyong LI. Stock market volatility prediction method based on improved genetic algorithm and graph neural network[J]. Journal of Computer Applications, 2022, 42(5): 1624-1633.

李晓寒, 贾华丁, 程雪, 李太勇. 基于改进遗传算法和图神经网络的股市波动预测方法[J]. 《计算机应用》唯一官方网站, 2022, 42(5): 1624-1633.

Figures/Tables 12

Fig. 1 Schematic diagram of proposed model framework

Fig. 2 Feature factors of stock market evaluation

Tab. 1 Common stock index parameters

指标	计算式	时间间隔/d	总数
最高价	$H t$	3，5，10，15	4
最低价	$L t$	3，5，10，15	4
开盘价	$O t$	3，5，10，15	4
复权后的收盘价	$C t$	3，5，10，15	4
成交量	$V t$	3，5，10，15	4
简单移动平均值	$(C t + C t - 1 + ⋯ + C t - n - 1) / n$	3，5，10，15	4
指数移动平均值	$(n) C t + (n - 1) C t - 1 + ⋯ + C t - (n - 1) n + (n - 1) + ⋯ + 1$	3，5，10，15	4
顺势指标	$(M t - S M t) / (0.015 D t)$	3，5，10，15	4
动量指标	$C t - C t - n$	3，5，10，15	4
动量指标%K	$C t - L L t - (n - 1) H H t - (n - 1) - L L t - (n - 1) × 100 %$	3，5，10，15	4
动量指标%D	$1 n ∑ i = 0 n - 1 K t - i × 100 %$	3，5，10，15	4
强力指数	$V t * [M A (C t, n) - M A (C t - 1, n)]$	3，5，10，15	4
重量指数	$∑ i = 1 25 E M A ((H t - L t), n) E M A (E M A ((H t - L t), n))$	3，5，10，15	4

Tab. 1 Common stock index parameters

指标	计算式	时间间隔/d	总数
最高价	$H t$	3，5，10，15	4
最低价	$L t$	3，5，10，15	4
开盘价	$O t$	3，5，10，15	4
复权后的收盘价	$C t$	3，5，10，15	4
成交量	$V t$	3，5，10，15	4
简单移动平均值	$(C t + C t - 1 + ⋯ + C t - n - 1) / n$	3，5，10，15	4
指数移动平均值	$(n) C t + (n - 1) C t - 1 + ⋯ + C t - (n - 1) n + (n - 1) + ⋯ + 1$	3，5，10，15	4
顺势指标	$(M t - S M t) / (0.015 D t)$	3，5，10，15	4
动量指标	$C t - C t - n$	3，5，10，15	4
动量指标%K	$C t - L L t - (n - 1) H H t - (n - 1) - L L t - (n - 1) × 100 %$	3，5，10，15	4
动量指标%D	$1 n ∑ i = 0 n - 1 K t - i × 100 %$	3，5，10，15	4
强力指数	$V t * [M A (C t, n) - M A (C t - 1, n)]$	3，5，10，15	4
重量指数	$∑ i = 1 25 E M A ((H t - L t), n) E M A (E M A ((H t - L t), n))$	3，5，10，15	4

Tab. 2 Confusion matrix

真实值	预测值
真实值	0	1
0	TP	FN
1	FP	TN

Tab. 3 Parameter setting of genetic algorithm

种群规模	交叉概率	变异概率
50	0.6	0.001
30	0.9	0.010
20	0.6	0.033

Fig. 3 Flow chart of stock market volatility prediction based on graph neural network

Tab. 4 Parameter setting of different algorithms

算法	设置
KNN	$n_n e i g h b o r s = 2$
SVM	$C = 0.8; k e r n e l = l i n e r; m a x_i t e r = 1 000$
LSTM	$r n n_u n i t = 10; l s t m_l a y e r s = 7; l r = 0.000 6$
NB	$n_c o m p o n e n t s = 5$
GNN	GRU， $s t e p = 26$

Tab. 4 Parameter setting of different algorithms

算法	设置
KNN	$n_n e i g h b o r s = 2$
SVM	$C = 0.8; k e r n e l = l i n e r; m a x_i t e r = 1 000$
LSTM	$r n n_u n i t = 10; l s t m_l a y e r s = 7; l r = 0.000 6$
NB	$n_c o m p o n e n t s = 5$
GNN	GRU， $s t e p = 26$

Fig. 4 Evolution processes of improved genetic algorithms

Tab. 5 Comparison of training time among different algorithms

股票	GA-KNN	IGA-KNN	GA-SVM	IGA-SVM	GA-LSTM	IGA-LSTM	GA-NB	IGA-NB	GA-GNN	IGA-GNN
AAPL	3 091.460 8	2 559.790 3	35 478.394 1	27 687.908 1	56 729.518 0	45 578.808 4	340.668 5	264.564 4	60 556.430 0	56 128.724 9
FB	3 294.147 5	2 631.970 2	28 466.057 2	27 166.509 0	58 280.310 9	45 084.564 1	314.441 3	261.400 9	63 682.432 6	57 763.346 7
TSLA	2 981.150 7	2 479.870 3	36 591.265 4	27 231.983 4	55 437.432 8	44 390.346 5	323.453 9	259.781 3	64 987.654 8	52 319.112 3
GM	2 153.981 4	1 733.313 1	34 840.073 6	26 841.766 5	44 695.818 8	34 769.764 2	312.948 8	252.872 1	58 764.761 2	48 342.563 4
IBM	3 432.666 6	2 635.527 5	27 549.382 4	26 822.657 7	54 596.064 7	45 357.892 9	326.622 2	257.484 4	64 578.006 7	53 217.342 7
MSFT	3 353.916 7	2 647.416 7	30 318.361 4	24 071.109 2	54 010.764 3	44 891.048 7	317.694 8	264.623 2	61 098.436 1	52 341.012 7
CAT	3 467.892 3	2 905.235 1	35 671.234 1	27 890.456 3	53 478.345 9	42 318.678 4	331.345 9	264.129 8	62 341.451 2	51 231.458 9
XOM	2 984.236 7	2 378.451 3	31 452.781 2	28 904.567 1	53 217.897 6	40 896.231 6	298.547 8	228.567 4	63 467.125 9	50 314.567 1
HD	3 678.892 3	2 876.123 5	34 512.123 8	30 789.123 5	49 865.234 5	35 671.238 9	312.897 1	243.123 9	59 873.129 8	49 237.458 1
SPY	3 789.345 1	2 876.126 1	33 456.239 0	26 891.458 1	52 341.569 8	41 237.892 3	332.567 1	256.564 3	64 349.123 9	53 219.456 1

Tab. 6 Comparison of accuracy among different algorithms

股票	KNN	IGA-KNN	SVM	IGA-SVM	LSTM	IGA-LSTM	NB	IGA-NB	GNN	IGA-GNN
AAPL	0.702 9	0.761 1	0.745 3	0.776 2	0.777 5	0.767 8	0.541 9	0.612 6	0.765 2	0.876 5
FB	0.709 7	0.760 5	0.773 4	0.778 3	0.716 6	0.756 4	0.565 2	0.649 5	0.713 4	0.872 3
TSLA	0.712 4	0.732 7	0.732 6	0.749 1	0.763 0	0.752 1	0.533 1	0.623 7	0.745 2	0.856 2
GM	0.692 5	0.758 2	0.749 3	0.782 3	0.595 5	0.761 6	0.565 7	0.650 8	0.682 3	0.867 5
IBM	0.726 8	0.758 4	0.787 7	0.786 4	0.453 7	0.762 7	0.561 8	0.644 7	0.723 5	0.879 0
MSFT	0.728 9	0.761 9	0.787 1	0.793 4	0.652 8	0.757 9	0.556 3	0.629 7	0.759 0	0.902 6
CAT	0.712 6	0.751 2	0.753 4	0.764 5	0.604 7	0.705 8	0.564 7	0.618 7	0.694 7	0.872 6
XOM	0.681 2	0.731 2	0.762 3	0.785 6	0.585 9	0.618 4	0.542 3	0.627 5	0.803 9	0.885 7
HD	0.702 7	0.725 1	0.758 3	0.762 3	0.483 4	0.652 7	0.564 8	0.634 7	0.729 4	0.867 2
SPY	0.721 2	0.748 7	0.769 1	0.796 1	0.671 6	0.710 4	0.531 2	0.617 9	0.705 1	0.878 9

Tab. 7 Stock evaluation indexes selected by IGA- GNN method

股票	MMT	CCI	SOD	FI	SOK	MI	Volume	EMA	Close	High	MA	Open	Low
AAPL	1	1	0	1	0	1	1	0	1	0	0	0	0
FB	1	1	1	0	0	1	1	1	1	1	0	0	0
TSLA	0	0	1	1	0	1	0	1	1	0	0	1	0
GM	1	1	1	1	0	1	0	1	1	0	0	0	1
IBM	1	0	1	1	1	1	1	0	1	0	1	0	1
MSFT	1	1	0	1	0	1	1	1	1	1	1	1	1
CAT	1	1	0	0	1	1	0	0	1	1	0	1	1
XOM	1	1	1	1	1	1	1	1	1	1	0	1	1
HD	0	1	1	1	1	1	1	1	1	0	1	0	1
SPY	1	1	1	1	0	1	0	1	1	1	0	1	0

Fig. 5 Investment returns of quantitative strategies in different algorithms

References 47

1	LO A W， MACKINLAY A C. Stock market prices do not follow random walks： evidence from a simple specification test ［J］. The Review of Financial Studies， 1988， 1（1）： 41-66. 10.1093/rfs/1.1.41
2	DIERKS T， ALLEN C. The TLS protocol version 1.0： RFC 2246 ［S］. Reston： Internet Society， 1999.
3	KIM K. Financial time series forecasting using support vector machines ［J］. Neurocomputing， 2003， 55（1/2）： 307-319. 10.1016/s0925-2312(03)00372-2
4	邓一沙.多层感知器神经网络构建交易策略——基于沪深300股指期货数据［D］.成都：西南财经大学，2012：62-71.
	DENG Y S. Building a trading strategy via multilayer perceptron neural network — base on the CSI300Stock index futures data ［D］. Chengdu： Southwestern University of Finance and Economics， 2012： 62-71.
5	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 2017 International Joint Conference on Neural Networks. Piscataway： IEEE， 2017： 1419-1426. 10.1109/ijcnn.2017.7966019
6	WHITE H. Economic prediction using neural networks： the case of IBM daily stock returns ［C］// Proceedings of the IEEE 1988 International Conference on Neural Networks. Piscataway： IEEE， 1988： 451-458. 10.1109/icnn.1988.23959
7	SELVIN S， VINAYAKUMAR R， GOPALAKRISHNAN E A， et al. Stock price prediction using LSTM， RNN and CNN-sliding window model ［C］// Proceedings of the 2017 International Conference on Advances in Computing， Communications and Informatics. Piscataway： IEEE， 2017： 1643-1647. 10.1109/icacci.2017.8126078
8	RATHER A M， AGARWAL A， SASTRY V N. Recurrent neural network and a hybrid model for prediction of stock returns ［J］. Expert Systems with Applications， 2015， 42（6）： 3234-3241. 10.1016/j.eswa.2014.12.003
9	JAHAN I， SAJAL S. Stock price prediction using Recurrent Neural Network （RNN） algorithm on time-series data ［EB/OL］. ［2021-01-12］. . 10.1109/eit.2019.8834336
10	HUANG C F， CHANG B R， CHENG D W， et al. Feature selection and parameter optimization of a fuzzy-based stock selection model using genetic algorithms ［J］. International Journal of Fuzzy Systems， 2012， 14（1）：65-75. doi:10.1142/S0219622012400135
11	HE Y Q， FATALIYEV K， WANG L P. Feature selection for stock market analysis ［C］// Proceedings of the 2013 International Conference on Neural Information Processing， LNCS 8227. Berlin： Springer， 2013： 737-744.
12	CHOU J S， NGUYEN T K. Forward forecast of stock price using sliding-window metaheuristic-optimized machine-learning regression ［J］. IEEE Transactions on Industrial Informatics， 2018， 14（7）： 3132-3142. 10.1109/tii.2018.2794389
13	BARON M， BROGAARD J， HAGSTRÖMER B， et al. Risk and return in high-frequency trading ［J］. Journal of Financial and Quantitative Analysis， 2019， 54（3）： 993-1024. 10.1017/s0022109018001096
14	BERAT SEZER O， OZBAYOGLU A M. Algorithmic financial trading with deep convolutional neural networks： time series to image conversion approach ［J］. Applied Soft Computing， 2018， 70： 525-538. 10.1016/j.asoc.2018.04.024
15	李立辉，田翔，杨海东，等.基于SVR的金融时间序列预测［J］.计算机工程与应用，2005，41（30）：221-224. 10.3321/j.issn:1002-8331.2005.30.070
	LI L H， TIAN X， YANG H D， et al. Financial time series forecasting based on SVR ［J］. Computer Engineering and Applications， 2005， 41（30）： 221-224. 10.3321/j.issn:1002-8331.2005.30.070
16	EDWARDS R D， MAGEE J， BASSETTI W H C. Technical Analysis of Stock Trends ［M］. 11th ed. Boca Raton： CRC Press， 2018： 34-45. 10.4324/9781315115719-12
17	JEGADEESH N， TITMAN S. Returns to buying winners and selling losers： implications for stock market efficiency ［J］. The Journal of Finance， 1993， 48（1）： 65-91. 10.1111/j.1540-6261.1993.tb04702.x
18	FAMA E F， FRENCH K R. Common risk factors in the returns on stocks and bonds ［J］. Journal of Financial Economics， 1993， 33（1）： 3-56. 10.1016/0304-405x(93)90023-5
19	TANG H， CHIU K C， XU L. Finite mixture of ARMA-GARCH model for stock price prediction ［EB/OL］. ［2021-03-10］. .
20	CHEN K， ZHOU Y， DAI F Y. A LSTM-based method for stock returns prediction： a case study of China stock market ［C］// Proceeding of 2015 IEEE International Conference on Big Data. Piscataway： IEEE， 2015： 2823-2824. 10.1109/bigdata.2015.7364089
21	李敏强，寇纪淞，林丹，等.遗传算法的基本理论与应用［M］.北京：科学出版社，2002：31-62.
	LI M Q， KOU J S， LIN D， et al. Basic Theory and Application of Genetic Algorithm ［M］. Beijing： Science Press， 2002： 31-62.
22	李壮年，储满生，柳政根，等.基于机器学习和遗传算法的高炉参数预测与优化［J］.东北大学学报（自然科学版），2020，41（9）：1262-1267. 10.12068/j.issn.1005-3026.2020.09.008
	LI Z N， CHU M S， LIU Z G， et al. Prediction and optimization of blast furnace parameters based on machine learning and genetic algorithm ［J］. Journal of Northeastern University （Natural Science）， 2020， 41（9）： 1262-1267. 10.12068/j.issn.1005-3026.2020.09.008
23	SILVA R C C， DE MENEZES JÚNIOR J M P， DE ARAÚJO JÚNIOR J M. Optimization of NARX neural models using PSO and GA algorithms applied to identification of photovoltaic systems ［J］. Journal of Solar Energy Engineering， 2021， 143（5）： Article No. 051001. 10.1115/1.4049718
24	孙波，姜平，周根荣，等.改进遗传算法在移动机器人路径规划中的应用［J］.计算机工程与应用，2019，55（17）：162-168. 10.3778/j.issn.1002-8331.1903-0387
	SUN B， JIANG P， ZHOU G R， et al. Application of improved genetic algorithm in path planning of mobile robots ［J］. Computer Engineering and Applications， 2019， 55（17）： 162-168. 10.3778/j.issn.1002-8331.1903-0387
25	WHITLEY D， STARKWEATHER T. GENITOR II： a distributed genetic algorithm ［J］. Journal of Experimental and Theoretical Artificial Intelligence， 1990， 2（3）： 189-214. 10.1080/09528139008953723
26	JIAO L C， WANG L. A novel genetic algorithm based on immunity［J］. IEEE Transactions on Systems， Man， and Cybernetics — Part A： Systems and Humans， 2000， 30（5）： 552-561. 10.1109/3468.867862
27	KIM K J， HAN I. Genetic algorithms approach to feature discretization in artificial neural networks for the prediction of stock price index ［J］. Expert Systems with Applications， 2000， 19（2）： 125-132. 10.1016/s0957-4174(00)00027-0
28	FANG Y， FATALIYEV K， WANG L P， et al. Improving the genetic-algorithm-optimized wavelet neural network for stock market prediction ［C］// Proceeding of the 2014 International Joint Conference on Neural Networks. Piscataway： IEEE， 2014： 3038-3042. 10.1109/ijcnn.2014.6889969
29	CHUNG H， SHIN K S. Genetic algorithm-optimized long short-term memory network for stock market prediction ［J］. Sustainability， 2018， 10（10）： Article No.3765. 10.3390/su10103765
30	BONDE G， KHALED R. Stock price prediction using genetic algorithms and evolution strategies ［EB/OL］. ［2021-02-10］. . 10.1109/iceca.2017.8212724
31	呼延康，樊鑫，余乐天，等.图神经网络回归的人脸超分辨率重建［J］.软件学报，2018，29（4）：914-925. 10.13328/j.cnki.jos.005405
	HU Y K， FAN X， YU L T， et al. Graph based neural network regression strategy for facial image super-resolution ［J］. Journal of Software， 2018， 29（4）： 914-925. 10.13328/j.cnki.jos.005405
32	BRUNA J， ZAREMBA W， SZLAM A， et al. Spectral networks and locally connected networks on graphs ［EB/OL］. ［2021-02-12］. .
33	DEFFERRARD M， BRESSON X， VANDERGHEYNST P. Convolutional neural networks on graphs with fast localized spectral filtering ［C］// Proceedings of the 2016 30th International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2016： 3844-3852.
34	KIPF T N， WELLING M. Semi-supervised classification with graph convolutional networks ［EB/OL］. ［2021-02-12］. .
35	KIM R， SO C H， JEONG M， et al. HATS： a hierarchical graph attention network for stock movement prediction ［EB/OL］. ［2021-02-12］. . 10.3390/app9224764
36	LIU J， LU Z C， DU W. Combining enterprise knowledge graph and news sentiment analysis for stock price volatility prediction ［EB/OL］. ［2021-02-10］. . 10.24251/hicss.2019.153
37	MATSUNAGA D， SUZUMURA T， TAKAHASHI T. Exploring graph neural networks for stock market predictions with rolling window analysis ［EB/OL］. ［2021-02-12］. .
38	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
39	BRONSTEIN M M， BRUNA J， LECUN Y， et al. Geometric deep learning： going beyond Euclidean data ［J］. IEEE Signal Processing Magazine， 2017， 34（4）： 18-42. 10.1109/msp.2017.2693418
40	DE JONG K A， SPEARS W M， GORDON D F. Using genetic algorithms for concept learning ［J］. Machine Learning， 1993， 13（2/3）： 161-188. 10.1007/bf00993042
41	HAMILTON W L， YING R， LESKOVEC J. Inductive representation learning on large graphs ［C］// Proceedings of the 2017 31st International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2017： 1025-1035. 10.1145/3219819.3219890
42	CHEN Y J， HAO Y T. A feature weighted support vector machine and K-nearest neighbor algorithm for stock market indices prediction ［J］. Expert Systems with Applications， 2017， 80：340-355. 10.1016/j.eswa.2017.02.044
43	LI Q， JIANG L L， LI P， et al. Tensor-based learning for predicting stock movements ［C］// Proceedings of the 2015 29th AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2015： 1784-1790. 10.1609/aaai.v33i01.33018650
44	LIU X W， DOU Y， YIN J P， et al. Multiple kernel k-means clustering with matrix-induced regularization ［C］// Proceedings of the 2016 30th AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2016： 1888-1894.
45	SHIHAVUDDIN A S M， AMBIA M N， AREFIN M M N， et al. Prediction of stock price analyzing the online financial news using Naive Bayes classifier and local economic trends ［C］// Proceedings of the 2010 3rd International Conference on Advanced Computer Theory and Engineering. Piscataway： IEEE， 2010： V4-22-V4-26. 10.1109/icacte.2010.5579624
46	VOSE M D. The Simple Genetic Algorithm： Foundations and Theory ［M］. Cambridge： MIT Press， 1999： 89-95.
47	JAFAR-ZANJANI S， INAMPUDI S， MOSALLAEI H. Adaptive genetic algorithm for optical metasurfaces design ［J］. Scientific Reports， 2018， 8： Article No.11040. 10.1038/s41598-018-29275-z

[1]	Tingjie TANG, Jiajin HUANG, Jin QIN. Session-based recommendation with graph auxiliary learning [J]. Journal of Computer Applications, 2024, 44(9): 2711-2718.
[2]	Hong CHEN, Bing QI, Haibo JIN, Cong WU, Li’ang ZHANG. Class-imbalanced traffic abnormal detection based on 1D-CNN and BiGRU [J]. Journal of Computer Applications, 2024, 44(8): 2493-2499.
[3]	Xuebin CHEN, Zhiqiang REN, Hongyang ZHANG. Review on security threats and defense measures in federated learning [J]. Journal of Computer Applications, 2024, 44(6): 1663-1672.
[4]	Zihao YAO, Yuanming LI, Ziqiang MA, Yang LI, Lianggen WEI. Multi-object cache side-channel attack detection model based on machine learning [J]. Journal of Computer Applications, 2024, 44(6): 1862-1871.
[5]	Xinrui LIN, Xiaofei WANG, Yan ZHU. Academic anomaly citation group detection based on local extended community detection [J]. Journal of Computer Applications, 2024, 44(6): 1855-1861.
[6]	Xuanfeng LI, Shengcai LIU, Ke TANG. Novel genetic algorithm for solving chance-constrained multiple-choice Knapsack problems [J]. Journal of Computer Applications, 2024, 44(5): 1378-1385.
[7]	Mingzhu LEI, Hao WANG, Rong JIA, Lin BAI, Xiaoying PAN. Oversampling algorithm based on synthesizing minority class samples using relationship between features [J]. Journal of Computer Applications, 2024, 44(5): 1428-1436.
[8]	Lin GAO, Yu ZHOU, Tak Wu KWONG. Evolutionary bi-level adaptive local feature selection [J]. Journal of Computer Applications, 2024, 44(5): 1408-1414.
[9]	Jie GUO, Jiayu LIN, Zuhong LIANG, Xiaobo LUO, Haitao SUN. Recommendation method based on knowledge‑awareness and cross-level contrastive learning [J]. Journal of Computer Applications, 2024, 44(4): 1121-1127.
[10]	Yi ZHENG, Cunyi LIAO, Tianqian ZHANG, Ji WANG, Shouyin LIU. Image denoising-based cell-level RSRP estimation method for urban areas [J]. Journal of Computer Applications, 2024, 44(3): 855-862.
[11]	Wei SHE, Yang LI, Lihong ZHONG, Defeng KONG, Zhao TIAN. Hyperparameter optimization for neural network based on improved real coding genetic algorithm [J]. Journal of Computer Applications, 2024, 44(3): 671-676.
[12]	Dapeng XU, Xinmin HOU. Feature selection method for graph neural network based on network architecture design [J]. Journal of Computer Applications, 2024, 44(3): 663-670.
[13]	Shengjie MENG, Wanjun YU, Ying CHEN. Feature selection algorithm for high-dimensional data with maximum correlation and maximum difference [J]. Journal of Computer Applications, 2024, 44(3): 767-771.
[14]	Lin SUN, Menghan LIU. K-means clustering based on adaptive cuckoo optimization feature selection [J]. Journal of Computer Applications, 2024, 44(3): 831-841.
[15]	Jingxin LIU, Wenjing HUANG, Liangsheng XU, Chong HUANG, Jiansheng WU. Unsupervised feature selection model with dictionary learning and sample correlation preservation [J]. Journal of Computer Applications, 2024, 44(12): 3766-3775.

Stock market volatility prediction method based on improved genetic algorithm and graph neural network

基于改进遗传算法和图神经网络的股市波动预测方法

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 12

References 47

Related Articles 15

Recommended Articles

Metrics