计算机科学 ›› 2023, Vol. 50 ›› Issue (11A): 221100039-7.doi: 10.11896/jsjkx.221100039
姚宏亮, 尹致远, 杨静, 俞奎
YAO Hongliang, YIN Zhiyuan, YANG Jing, YU Kui
摘要： 股票市场是一个复杂非线性动态系统,具有高度不确定性和多变性,股市趋势预测是数据挖掘领域的一个研究热点。针对基于数据驱动方法所生成的模型鲁棒性差,训练良好的模型不适应实际需要的问题,提出了一种多Agent博弈动态影响图模型( Mulit-Agent Game Dynamic Influence Diagrams,MAGDIDs)。首先,从博弈的角度引入多方和空方作为股市的行为主体(Agent),提取行为主体的相关特征;然后,利用能量表示博弈主体的力量大小,并对行为主体特征进行量化融合;进而引入博弈策略,构建多Agent博弈动态影响图模型,对于股市行为主体的博弈过程进行建模;最后,利用联合树的自动推理技术,预测股市趋势。在实际数据上进行实验,实验结果表明多空博弈趋势预测算法具有良好性能。
中图分类号:
| [1]ZHANG D H,LOU S.The application research of neural network and BP algorithm in stock price pattern classification and prediction[J].Future Generation Computer Systems,2021,115:872-879. [2]DE OLIVERIRA F A,NOBRE C N,ZARATE L E.ApplyingArtificial Neural Networks to prediction of stock price and improvement of the directional prediction index-Case study of PETR4,Petrobras,Brazil[J].Expert Systems with Applications,2013,40(18):7596-7606. [3]ZHAO Z Y,RAO R N,TU S X,et al.Time-weighted LSTM model with redefined labeling for stock trend prediction[C]//2017 IEEE 29th International Conference on Tools with Artificial Intelligence(ICTAI).IEEE,2017:1210-1217. [4]SELVIN S,VINAYAKAKUMAR R,GOPALAKRISHNAN EA,et al.Stock priceprediction using LSTM,RNN and CNN-sli-ding window model[C]//2017 International Conference on Advances in Computing,Communications and Informatics(ICACCI).IEEE,2017:1643-1647. [5]OJO S O,OWOLAWI P,MPHAHLELE M,et al.Stock Market Behaviour Prediction using Stacked LSTM Networks[C]//2019 International Multidisciplinary Information Technology and Engineering Conference(IMITEC).IEEE,2020:1-5. [6]HOOI B,LIU S,SMAILAGIC A,et al.BEATLEX:Summari-zing and Forecasting Time Series with Patterns[C]//Joint European Conference on Machine Learning and Knowledge Disco-very in Databases.Cham:Springer,2017:3-19. [7]QIN X Y,PENG Q K.Stock turning point recognition usingmultiplemodel algorithm with multiple types of features[C]//Proceedings of the 10th World Congress on Intelligent Control and Automation.IEEE,2012:4020-4025. [8]CHANDRIKKA P V,VISALAKKSHMI K,SRINIVASAN KS.Application of Hidden Markov Models in Stock Trading[C]//2020 6th International Conference on Advanced Computing and Communication Systems(ICACCS).IEEE,2020:1144-1147. [9]CHENG S H.A Hybrid Predicting Stock Return Model Basedon Bayesian Network and Decision Tree[C]//2014 6th International Conference on Industrial.Springer International Publi-shing,2014:218-227. [10]LIU Z X,DANG Z Y,YU J.Stock Price Prediction Model Based on RBF-SVM Algorithm[C]//2020 International Conference on Computer Engineering and Intelligent Control(ICCEIC).IEEE,2020:124-127. [11]HERNANDEZ-LEAL P,KAISERS M,BAARSLAG T,et al.A Survey of Learning in Multiagent Environments:Dealing with Non-Stationarity[J].arXiv:1707.09183,2017. [12]SILVER D,HUANG A,MADDISON C J,et al.Mastering the game of Go with deep neural networks and tree search[J].Nature,2016,529(7587):484-489. [13]MORAVCIK M,SCHMID M,BURCH N,et al.DeepStack:Expert-level artificial intelligence in heads-up no-limit poker[J].Science,2017,356(6337):508-513. [14]HOWARD R A,MATHESON J E.Influence Diagrams[J].Principles & Applications of Decision Analysis,2005,2(3):127-143. [15]KOLLER D,MILCH B.Multi-agent influence diagrams for representing and solving games[J].Games and Economic Beha-vior,2003,45(1):181-221. [16]DOSHI P,ZENG Y,CHEN Q.Graphical models for interactive POMDPs:representation and solutions[J].Autonomous Agents and Multi-Agent Systems,2009,18(3):376-416. [17]YAO H L,WANG H,ZHANG Y S,et al.Research on multi-agent dynamic influence diagrams and its approximate inference algorithm[J].Chinese Journal of Computers,2008,31(2):236-244. [18]COOPER G F.A Method for Using Belief Networks as In-fluence Diagrams[C]//4th Workshop on Uncertainty in Artificial Intelligence.2013:55-63. [19]ZHOU L,YIN Q Y,HUANG K Q.Game-Theoretic Learning in Human-Computer Gaming[J].Chinese Journal of Computers,2022,45(9):1859-1876. |
|
||
首页