ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2019, Vol. 56 ›› Issue (8): 1621-1631.doi: 10.7544/issn1000-1239.2019.20190330

所属专题: 2019人工智能前沿进展专题

• 人工智能 • 上一篇    下一篇

基于深度神经网络结构的互联网金融市场动态预测

赵洪科1,吴李康2,李徵2,张兮1,刘淇2,陈恩红2   

  1. 1(天津大学管理与经济学部 天津 300072);2(大数据分析与应用安徽省重点实验室(中国科学技术大学) 合肥 230027) (hongke@tju.edu.cn)
  • 出版日期: 2019-08-01
  • 基金资助: 
    国家自然科学基金项目(71790594,71722005)

Predicting the Dynamics in Internet Finance Based on Deep Neural Network Structure

Zhao Hongke1, Wu Likang2, Li Zhi2, Zhang Xi1, Liu Qi2, Chen Enhong2   

  1. 1(College of Management and Economics, Tianjin University, Tianjin 300072);2(Anhui Province Key Laboratory of Big Data Analysis and Application (University of Science and Technology of China), Hefei 230027)
  • Online: 2019-08-01

摘要: 近些年,互联网金融市场在国内外迅速发展;同时,针对互联网金融市场的研究也成为了学术界的热点.相比于传统金融市场,互联网金融市场具有更高的流动性和易变性.针对互联网金融市场的动态(日交易量和日交易次数)进行研究,提出了基于深度神经网络结构的融合层次时间序列学习的预测模型.首先,该模型可以实现对多序列(市场宏观动态序列和多种子序列)特征变量输入的处理,并且在时间和序列特征2个维度上利用注意力机制来融合输入变量.其次,模型设计了基于预测序列平稳性约束的优化函数,使得模型具有更好的稳健性.最后,在真实的大规模数据集上进行了大量的实验,结果充分证明了所提出的模型在互联网金融市场动态预测问题上的有效性与稳健性.

关键词: 互联网金融, 时间序列, 动态预测, 深度神经网络, 序列建模

Abstract: In recent years, the Internet financial market has achieved rapid development across the globe. In the meantime, Internet finance has become a hot topic in academia. Compared with traditional financial markets, the Internet financial market has higher liquidity and volatility. In this paper, the dynamics (daily trading amount and count) of the Internet financial market is studied and a prediction model is proposed based on deep neural network for fusion hierarchical time series learning. Firstly, the model can process the multiple sequence (macro dynamic sequence and multiple subsequences) feature as the input variables. And then, an attention mechanism is proposed to fuse the input variables from both the time and subsequence feature dimensions. Next, the model designs an optimization function based on the stability constraint of the sequence prediction, which makes the model have better robustness. Finally, a large number of experiments have been carried out on real large-scale data sets, and the results have fully proved the effectiveness and robustness of the proposed model in the dynamic prediction of Internet finance market.

Key words: Internet finance, time series, dynamic prediction, deep neural network, sequential modeling

中图分类号: