Solving the Limitations of Forecasting Time Series Model by Independent Component Analysis Approach

J.-C. Lin, Y.-H. Li, and C.-H. Liu (Taiwan)


Independent component analysis(ICA), Autoregres sive(AR), ambiguity, correlation.


Recently some scholars build time series forecasting model by independent component analysis mechanism. Within component ambiguity , time series approximation and mean difference problems, independent component analy sis mechanism has intrinsic limitations for time series fore casting. Solutions for those limitations were purposed in this paper. Under the linear time complexity, those lim itations were solved by our proposed methods to ensure the forecasting reward. The empirical data show that our model exactly reveals the flexibility and accuracy in time series forecasting domain.

Important Links:

Go Back