Journal of Computer Applications ›› 2019, Vol. 39 ›› Issue (4): 1046-1052.DOI: 10.11772/j.issn.1001-9081.2018091882

Previous Articles     Next Articles

Time series trend prediction at multiple time scales

WANG Jince, DENG Yueping, SHI Ming, ZHOU Yunfei   

  1. Department of Computer and Information Engineering, Shanxi Institute of Energy, Jinzhong Shanxi 030600, China
  • Received:2018-09-10 Revised:2018-10-18 Online:2019-04-10 Published:2019-04-10

多时间尺度时间序列趋势预测

王金策, 邓越萍, 史明, 周云飞   

  1. 山西能源学院 计算机与信息工程系, 山西 晋中 030600
  • 通讯作者: 周云飞
  • 作者简介:王金策(1990-),男,河北衡水人,助教,硕士,主要研究方向:数据挖掘、机器学习;邓越萍(1965-),女,山西平遥人,副教授,硕士,主要研究方向:数据库、软件测试;史明(1973-),男,山西长治人,副教授,硕士,主要研究方向:网站建设、信息管理;周云飞(1983-),男,河北张家口人,讲师,博士,主要研究方向:虚拟现实、数值模拟。

Abstract: A time series trend prediction algorithm at multiple time scales based on novel feature model was proposed to solve the trend prediction problem of stock and fund time series data. Firstly, a feature tree with multiple time scales of features was extracted from original time series, which described time series with the characteristics of the series in each level and relationship between levels. Then, the hidden states in feature sequences were extracted by clustering. Finally, a Multiple Time Scaled Trend Prediction Algorithm (MTSTPA) was designed by using Hidden Markov Model (HMM) to simultaneously predict the trend and length of the trends at different scales. In the experiments on real stock datasets, the prediction accuracy at every scale are more than 60%. Compared with the algorithm without using feature tree, the model using the feature tree is more efficient, and the accuracy is up to 10 percentage points higher at a certain scale. At the same time, compared with the classical Auto-Regressive Moving Average (ARMA) model and pattern-based Hidden Markov Model (PHMM), MTSTPA performs better, verifying the validity of MTSTPA.

Key words: feature tree, time series prediction, trend prediction at multiple time scales, Hidden Markov Model (HMM)

摘要: 针对股票、基金等大量时间序列数据的趋势预测问题,提出一种基于新颖特征模型的多时间尺度时间序列趋势预测算法。首先,在原始时间序列中提取带有多时间尺度特征的特征树,其刻画了时间序列,不仅带有序列在各个层次的特征,同时表示了层次之间的关系。然后,利用聚类挖掘特征序列中的隐含状态。最后,应用隐马尔可夫模型(HMM)设计一个多时间尺度趋势预测算法(MTSTPA),同时对不同尺度下的趋势以及趋势的长度作出预测。在真实股票数据集上的实验中,在各个尺度上的预测准确率均在60%以上,与未使用特征树对比,使用特征树的模型预测效率更高,在某一尺度上准确率高出10个百分点以上。同时,与经典自回归滑动平均模型(ARMA)模型和PHMM(Pattern-based HMM)对比,MTSTPA表现更优,验证了其有效性。

关键词: 特征树, 时间序列预测, 多时间尺度趋势预测, 隐马尔可夫模型

CLC Number: