Conference Paper

A Novel Time Series Forecasting Approach with Multi-Level Data Decomposing and Modeling

Coll. of Comput. Sci., Zhejiang Univ., Hangzhou
DOI: 10.1109/WCICA.2006.1712645 Conference: Intelligent Control and Automation, 2006. WCICA 2006. The Sixth World Congress on, Volume: 1
Source: IEEE Xplore

ABSTRACT Time series produced in complex systems are always controlled by multi-level laws, including macroscopic and microscopic laws. These multi-level laws bring on the combination of long-memory effects and short-term irregular fluctuations in the same series. Traditional analysis and forecasting methods do not distinguish these multi-level influences and always make a single model for prediction, which has to introduce a lot of parameters to describe the characteristics of complex systems and results in the loss of efficiency or accuracy. This paper goes deep into the structure of series data, decomposes time series into several simpler ones with different smoothness, and then samples them with multi-scale sizes. After that, each time series is modeled and predicated respectively, and their results are integrated finally. The experimental results on the stock forecasting show that the method is effective and satisfying, even for the time series with large fluctuations

7 Reads
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper evaluates different procedures for selecting the order of a non-seasonal ARMA model. Specifically, it compares the forecasting accuracy of models developed by the personalized Box-Jenkins (BJ) methodology with models chosen by numerous automatic procedures. The study uses real series modelled by experts (textbook authors) in the BJ approach. Our results show that many objective selection criteria provide structures equal or superior to the time-consuming BJ method. For the sets of data used in this study, we also examine the influence of parsimony in time-series forecasting. Defining what models are too large or too small is sensitive to the forecast horizon. Automatic techniques that select the best models for forecasting are similar in size to BJ models although they often disagree on model order.
    Journal of Forecasting 09/2009; 13(5):419 - 434. DOI:10.1002/for.3980130502 · 0.93 Impact Factor
  • Source
    Proceedings of the National Academy of Sciences 02/1956; 42(1):43-7. DOI:10.1073/pnas.42.1.43 · 9.67 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper introduces several prediction models for short-term random walk forecasting like stock price indexes forecasting. The radial basis function neural net (RBFNN) is widely applied to function approximation or classification issues. An autoregressive moving-average method has been utilized on the topic of time series. SVR-GM(1,1|τ) model employ the support vector machines (SVM) learning algorithm to improve the control and environment parameters in GM(1,1|τ) model, that is, enhancing generalization capability in the non-periodic short-term prediction. Therefore, this proposed method could smooth the overshooting problem, that often occurred in GM(1,1|τ) model or autoregressive moving-average (ARMA) method, so as to achieve better prediction accuracy. Finally, the comparison of performance on international stock price indexes forecasting between the various models has been done.
    Neural Networks, 2003. Proceedings of the International Joint Conference on; 08/2003
Show more

Preview (2 Sources)

7 Reads
Available from