Self-organization map method for pattern matching of stock time series

被引：0
作者：
Guo, Wei [1 ]
He, Pilian [1 ]
Wang, Zhong [1 ]
机构：
[1] Tianjin Univ, Dept Comp Sci, Tianjin 300072, Peoples R China
来源：
Proceedings of 2006 International Conference on Artificial Intelligence: 50 YEARS' ACHIEVEMENTS, FUTURE DIRECTIONS AND SOCIAL IMPACTS | 2006年
关键词：
self-organization map; time series; patterns stock;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
It is difficult to forecast the tendency for stock market since it is a typical non-linear dynamic system. With proper experiences in share market, people can know more about stock time series patterns. Consequently they can determine how and when to invest by use of these patterns. But it is difficult for them to handle such large data set. This paper presents a method of patterns mining for stock time series by use of Self-organization map. Because of considerations in investment income and risk control, there are. 30 dimensions for inputs and 50 for outputs. This method will be helpful in improving stock patterns mining for future investment reference.
引用
收藏
页码：118 / 121
页数：4
相关论文
共 41 条
  • [1] Time series prediction method based on pattern matching
    Xie, Yonghong
    Wulamu, Aziguli
    He, Qing
    Liu, Xiaobin
    Journal of Computational Information Systems, 2014, 10 (13): : 5773 - 5784
  • [2] Evolution based self-organization of structures in linear time-series modeling
    Hyotyniemi, H
    Nissinen, AS
    Koivo, HN
    PROCEEDINGS OF THE THIRD NORDIC WORKSHOP ON GENETIC ALGORITHMS AND THEIR APPLICATIONS (3NWGA), 1997, : 135 - 152
  • [3] Time-series prediction modelling based on an efficient self-organization learning neural network
    Yang, Gang
    Yang, Hui
    Dai, Lizhen
    IFAC PAPERSONLINE, 2015, 48 (08): : 248 - 253
  • [4] Time Series Prediction Using Pattern Matching
    Nguyen Thanh Son
    Nguyen Hoai Le
    Duong Tuan Anh
    2013 INTERNATIONAL CONFERENCE ON COMPUTING, MANAGEMENT AND TELECOMMUNICATIONS (COMMANTEL), 2013, : 401 - 406
  • [5] Hierarchical pattern matching for anomaly detection in time series
    Van Onsem, M.
    De Paepe, D.
    Vanden Hautte, S.
    Bonte, P.
    Ledoux, V
    Lejon, A.
    Ongenae, F.
    Dreesen, D.
    Van Hoecke, S.
    COMPUTER COMMUNICATIONS, 2022, 193 : 75 - 81
  • [6] Case-base maintenance in an associative memory organized by a self-organization map
    Fornells, A.
    Golobardes, E.
    INNOVATIONS IN HYBRID INTELLIGENT SYSTEMS, 2007, 44 : 312 - 319
  • [7] Research on the Text Classification Method with Self-Organization Network Model
    Chen, Jian
    Jiang, Wenrong
    Yan, Jihong
    MATERIALS SCIENCE AND ENGINEERING, PTS 1-2, 2011, 179-180 : 940 - 944
  • [8] A novel price-pattern detection method based on time series to forecast stock markets
    Chen, Tai-Liang
    Su, Chung-Ho
    Cheng, Ching-Hsu
    Chiang, Hung-Hsing
    AFRICAN JOURNAL OF BUSINESS MANAGEMENT, 2011, 5 (13): : 5188 - 5198
  • [9] Segmentation extraction of feature points for time series pattern matching
    Li Z.
    Liu C.
    Wu S.
    Guo J.
    Beijing Hangkong Hangtian Daxue Xuebao/Journal of Beijing University of Aeronautics and Astronautics, 2023, 49 (07): : 1593 - 1599
  • [10] Feedback-Driven Pattern Matching in Time Series Data
    Van Onsem, M.
    Ledoux, V.
    Melange, W.
    Dreesen, D.
    Van Hoecke, S.
    IEEE ACCESS, 2025, 13 : 1764 - 1777
12345