Multiscale Forecasting Models

Laser 1 Dec 2022 08:53 LEARNING » e-book

Multiscale Forecasting Models
English | PDF,EPUB | 2018 | 141 Pages | ISBN : 3319949918 | 35.57 MB

This book presents two new decomposition methods to decompose a series in intrinsic components of low and high frequencies.

The methods are based on Singular Value Decomposition (SVD) of a Hankel matrix (HSVD). The proposed decomposition is used to improve the accuracy of linear and nonlinear auto-regressive models.
Linear Auto-regressive models (AR, ARMA and ARIMA) and Auto-regressive Neural Networks (ANNs) have been found insufficient because of the highly complicated nature of some series. Hybrid models are a recent solution to deal with non-stationary processes which combine pre-processing techniques with conventional forecasters, some pre-processing techniques broadly implemented are Singular Spectrum Analysis (SSA) and Stationary Wavelet Transform (SWT). Although the flexibility of SSA and SWT allows their usage in a wide range of forecast problems, there is a lack of standard methods to select their parameters.

The proposed decomposition HSVD and Multilevel SVD are described in detail through series coming from the transport and fishery sectors. Further, for comparison purposes, it is evaluated the forecast accuracy reached by SSA and SWT, both jointly with AR-based models and ANNs.



Add Comment

  • People and smileys emojis
    Animals and nature emojis
    Food and drinks emojis
    Activities emojis
    Travelling and places emojis
    Objects emojis
    Symbols emojis
    Flags emojis