改进的多层图注意力网络在股价预测中的应用

doi:10.3778/j.issn.1002-8331.2008-0337

摘要/Abstract

摘要： 利用关系数据进行股价预测的方法最近已经被提出，但目前还没有找到一种有效的方法可以有选择地聚合不同类型的关系数据去预测股价。提出一种改进的多层节点图注意力网络（FHAN）模型，该方法融合Fraudar算法，提供了一种对多个对象关系之间看问题的视角。模型把公司看做节点，把交互看成边，选择性地聚合不同关系类型的信息，并将这些信息添加到每个公司的节点表示中，添加了信息的节点表示被输入到特定任务层自动选择信息，实验结果表明，该方法比目前流行的神经网络算法在股价预测的效果上更准确，实验选取不同神经网络算法做对比，在最优参数条件下，采用该方法比现有方法准确率平均提高约4%，最高提高约24%。

关键词: 股价预测, 多层节点图注意力网络, 关系数据

Abstract: Methods of useing relational data for stock market prediction have been recently proposed. No existing work on stock market prediction has an effective way to selectively aggregate information on different relation types. To address this, FHAN model include Fraudar method, provides a perspective to see the relationship between multiple objects. The model regards the company as a node and the interaction as an edge, which selectively aggregates information on different relation types and adds the information to the representations of each company. Node representations with the added information are fed into a task-specific layer. FHAN which can automatically select information outperformed all the existing main methods.

Key words: stock market prediction, multilayer node-graph attention network（FHAN), relational data

姜明华, 陈赟. 改进的多层图注意力网络在股价预测中的应用[J]. 计算机工程与应用, 2022, 58(3): 308-314.

JIANG Minghua, CHEN Yun. Prediction of Stock on Improved Hierarchical Graph Attention Network[J]. Computer Engineering and Applications, 2022, 58(3): 308-314.

参考文献

[1] AGRAWAL J G，CHOURASIA V S，MITTRA A K.State of the art in stock prediction techniques[J].International Journal of Advanced Research in Electrical，Electronics and Instrumentation Engineering，2013，34（2）：1360-1361.
[2] BAO W，YUE J，RAO Y.deep learning framework for financial time series using stacked auto encoders and long-short term memory[J].PloSone，2017，18（9）：44.
[3] BOLLERSLEV T，MARRONE J，XU L，et al.Stock return predictability and variance risk premia[J]Journal of Financial and Quantitative Analysis，2014，49（9）：633-661.
[4] CHEN Y，WEI Z，HUANG X.Incorporating corporation relationship via graph convolutional neural networks for stock price prediction[C]//Proceedings of the 27th ACM International Conference on Information and Knowledge Management，2018.
[5] CHEN J，MA T，XIAO C.Fastlearning with graph convolutional networks via importance sampling[C]//International Conference on Learning Representations，2018.
[6] HOOL B.Bounding graph fraud in the face of camouflage[C]//22nd ACM SIGKDD International Conference，2016.
[7] DEMPSTER M，PAYNE W，ROMAHI Y，et al.Computational learning techniques for trading using populartechnical indicators[J].IEEE Transactions on Neural Networks，2001，12（7）：744-754.
[8] DING X，ZHANG Y，LIU T，et al.Knowledge driven event embedding for stock prediction[C]//The 26th International Conference on Computational Linguistics，2016：2133-2142.
[9] FENG F，HE X，WANG X，et al.Temporal relational ranking for stock prediction[J].ACM Transactions on Information Systems（TOIS），2019，37（2）.
[10] GILMER J，SCHOENHOLZ S，RILEY P，et al.Neuralmessage passing for quantum chemistry[C]//Proceedings of the 34th International Conference on Machine Learning，2017：1263-1272.
[11] HAMILTON W，YING Z，LESKOVEC J，et al.Inductive representation learning on large graphs[C]//Advances in Neural Information Processing Systems，2017.
[12] LI X，XIE H，CHEN L，et al.News impact on stock price return via sentiment analysis[J].Knowledge Based Systems，2014，69（2）：14-23.
[13] PATEL J，SHAH S，THAKKAR P，et al.Predicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques[J].Expert Systems with Applications，2015，42（1）：259-268.
[14] RATHER A，AGARWAL A，SASTRY V，et al.Recurrent neural net work and a hybrid model for prediction of stock returns[J].Expert Systems with Applications，2015，42（1）：3234-3241.
[15] HELCL J，LIBOVICKYA A J.Neural monkey：an open-source tool for sequence learning[J].Prague Bulletin of Mathematical Linguistics，2017，107（1）：5-17.
[16] VRANDECIC D，KRO?TZSC M.Wikidata：a free collaborative knowledge base[J].Communications of the ACM，2014，57（10）：78-85.
[17] SUN Y Z，HAN J W，YAN X F，et al.Meta path-based top-K similarity search in heterogeneous information networks[J].Proceedings of the VLDB Endowment，2011，4（11）：992-1003.
[18] SUNDERMEYER M，SCHLUTER R，NEY H.LSTM neural networks for language model[C]//13th Annual Conference on Inter Speech，2012：601-608.