J.D. Wichard and M. Ogorzałek (Poland)
Modelling, Time Series Prediction, Ensemble Models
We describe the use of ensemble methods to build proper models time series prediction. Our approach extends the classical ensemble methods for neural networks by using several different model architectures. We further suggest an iterated prediction procedure to select the final ensem ble members. This is an extension of well know the cross validation scheme for model validation.
Important Links:
Go Back
