Journal of Computer Applications ›› 2020, Vol. 40 ›› Issue (5): 1501-1509.DOI: 10.11772/j.issn.1001-9081.2019091678

• Frontier & interdisciplinary applications • Previous Articles     Next Articles

Stock closing price prediction algorithm using adaptive whale optimization algorithm and Elman neural network

ZHU Changsheng1, KANG Lianghe1, FENG Wenfang2   

  1. 1.College of Computer and Communications, Lanzhou University of Technology, LanzhouGansu 730050, China
    2.School of Economics and Management, Lanzhou University of Technology, LanzhouGansu 730050, China
  • Received:2019-10-08 Revised:2019-12-02 Online:2020-05-10 Published:2020-05-15
  • Contact: KANG Lianghe, born in 1987, M. S. candidate. Her research interests include cloud computing, big data.
  • About author:ZHU Changsheng, born in 1972, Ph. D., professor. His research interests include high performance computing, big data.KANG Lianghe, born in 1987, M. S. candidate. Her research interests include cloud computing, big data.FENG Wenfang, born in 1979, Ph. D., professor. Her research interests include investment theory, big data.

基于自适应鲸鱼优化算法结合Elman神经网络的股市收盘价预测算法

朱昶胜1, 康亮河1, 冯文芳2   

  1. 1.兰州理工大学 计算机与通信学院,兰州 730050
    2.兰州理工大学 经济管理学院,兰州 730050
  • 通讯作者: 康亮河(1987—)
  • 作者简介:朱昶胜(1972—),男,甘肃秦安人,教授,博士,主要研究方向:高性能计算、大数据; 康亮河(1987—),女,甘肃会宁人,硕士研究生,主要研究方向:云计算、大数据; 冯文芳(1976—),女,甘肃天水人,副教授,博士,主要研究方向:投资理论、大数据。

Abstract:

Focused on the issue that Elman neural network has slow convergence speed and low prediction accuracy in the closing price prediction based on the network public opinion of the stock market, a prediction model combining Improved Whale Optimization Algorithm (IWOA) and Elman neural network was proposed, which is based on Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN)algorithm. Firstly, text mining technology was used to mine and quantify the network public opinions of Shanghai Stock Exchange (SSE) 180 shares, and in order to reduce the complexity of attribute set, Boruta algorithm was used to select the important attributes. Then, CEEMDAN algorithm was used to add a certain number of white noises with specific variances in order to realize the decomposition and noise reduction of the attribute sequence. At the same time, in order to enhance the global search and local mining capabilities, adaptive weight was used to improve Whale Optimization Algorithm (WOA). Finally, the initial weights and thresholds of Elman neural network were optimized by WOA in the iterative process. The results show that, compared to Elman neural network, the proposed model has the Mean Absolute Error (MAE) reduced from 358.812 0 to 113.055 3; compared to the original dataset without CEEMDAN algorithm, the proposed model has the Mean Absolute Percentage Error (MAPE) reduced from 4.942 3% to 1.445 31%, demonstrating that the model effectively improves the prediction accuracy and provides an effective experimental method for predicting the network public opinion of stock market.

Key words: network public opinion, text mining, Whale Optimization Algorithm (WOA), Elman neural network

摘要:

针对Elman神经网络在基于股市网络舆情的收盘价预测中存在的收敛速度慢且预测精度低的问题,提出了结合基于自适应噪声的完全集合经验模态分解(CEEMDAN)的改进鲸鱼优化算法(IWOA)结合Elman神经网络预测模型。首先,通过文本挖掘技术对上海证券交易所股票价格综合指数(SSE)180股的网络舆情进行挖掘和量化,并利用Boruta算法筛选重要属性以降低属性集的复杂度;然后,通过CEEMDAN算法在属性集中添加一定数量特定方差的白噪声,实现属性序列的分解与降噪;同时,利用自适应权重改进鲸鱼优化算法(WOA)以增强其全局搜索及局部开采能力;最后,利用WOA在迭代过程中不断优化Elman神经网络的初始权重和阈值。结果表明:比起单独使用Elman神经网络,所提模型的平均绝对误差(MAE)从358.812 0降低至113.055 3;与未采用CEEMDAN算法的原始数据集相比,该模型的平均绝对百分比误差(MAPE)从4.942 3%降低到1.445 31%,说明所提模型有效提高了预测精度,为股市网络舆情的预测提供了一种有效的实验方法。

关键词: 网络舆情, 文本挖掘, 鲸鱼优化算法, Elman神经网络

CLC Number: