Neural Network Model Selection for Financial Time Series Prediction

被引:0
|
作者
Francesco Virili
Bernd Freisleben
机构
[1] University of Siegen,Department of Information Systems
[2] University of Siegen,Department of Electrical Engineering & Computer Science
来源
Computational Statistics | 2001年 / 16卷
关键词
neural networks; model selection; time series;
D O I
暂无
中图分类号
学科分类号
摘要
Can neural network model selection be guided by statistical procedures such as hypothesis tests, information criteria and cross-validation? Recently, Anders and Korn (1999) proposed five neural network model specification strategies based on different statistical procedures. In this paper, we use and adapt the Anders-Korn framework to find appropriate neural network models for financial time series prediction. The most important new issue in this context is the specification of the dynamic structure of the models, i.e. the selection of the lagged values of the input time series. A linear model is built with full dynamic structure, then its possible nonlinear extensions are tested using a statistical procedure inspired by the Anders-Korn approach. Promising results are obtained with an application to predict the monthly time series of mortgage loans purchased in The Netherlands.
引用
收藏
页码:451 / 463
页数:12
相关论文
共 50 条
  • [31] Comparison of GARCH, Neural Network and Support Vector Machine in Financial Time Series Prediction
    Hossain, Altaf
    Zaman, Faisal
    Nasser, M.
    Islam, M. Mufakhkharul
    PATTERN RECOGNITION AND MACHINE INTELLIGENCE, PROCEEDINGS, 2009, 5909 : 597 - +
  • [32] A novel nonlinear neural network ensemble model for financial time series forecasting
    Lai, Kin Keung
    Yu, Lean
    Wang, Shouyang
    Wei, Huang
    COMPUTATIONAL SCIENCE - ICCS 2006, PT 1, PROCEEDINGS, 2006, 3991 : 790 - 793
  • [33] Improved CBP Neural Network Model with Applications in Time Series Prediction
    Dai Qun
    Chen Songcan
    Zhang Benzhu
    Neural Processing Letters, 2003, 18 (3) : 217 - 231
  • [34] Energy Output Prediction Model on Time Series Analysis and Neural Network
    Feng Sbu-hu
    Guan Xiao-ji
    2007 INTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATIONS, NETWORKING AND MOBILE COMPUTING, VOLS 1-15, 2007, : 5021 - +
  • [35] Chaotic time series prediction with a global model: Artificial neural network
    Karunasinghe, Dulakshi S. K.
    Liong, Shie-Yui
    JOURNAL OF HYDROLOGY, 2006, 323 (1-4) : 92 - 105
  • [36] Improved CBP neural network model with applications in time series prediction
    Dai, Q
    Chen, SC
    Zhang, BZ
    NEURAL PROCESSING LETTERS, 2003, 18 (03) : 197 - 211
  • [37] Time series prediction using fuzzy wavelet neural network model
    Abiyev, Rahib H.
    ARTIFICIAL NEURAL NETWORKS - ICANN 2006, PT 2, 2006, 4132 : 191 - 200
  • [38] Bayesian regularization neural network model for stock time series prediction
    Hou Y.
    Xie B.
    Liu H.
    International Journal of Performability Engineering, 2019, 15 (12): : 3271 - 3278
  • [39] USING NEURAL NETWORK IN FINANCIAL TIME SERIES ANALYSIS
    Glova, Jozef
    Gavurova, Beata
    ICT FOR COMPETITIVENESS 2012, 2012, : 109 - 117
  • [40] Neural network and time series identification and prediction
    Neji, Z
    Beji, FM
    IJCNN 2000: PROCEEDINGS OF THE IEEE-INNS-ENNS INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOL IV, 2000, : 461 - 466