Wavelet- and SVM-based forecasts: An analysis of the U.S. metal and materials manufacturing industry

Viviana Fernandez

doi:10.1016/j.resourpol.2007.06.002

Wavelet- and SVM-based forecasts: An analysis of the U.S. metal and materials manufacturing industry

Viviana Fernandez

Business School

Research output: Contribution to journal › Article › peer-review

37 Scopus citations

Abstract

This article compares four non-linear forecasting methods: multiplicative seasonal ARIMA, unobserved components (UC), wavelet-based and support vector machines (SVM). Whereas the first two methods are well known in the time series field, the other two rely on recently developed mathematical techniques. Based on forecasting accuracy and encompassing tests applied to shipments data of the U.S. metal and material manufacturing industry for 1958-2000, we conclude that that these two novel forecast techniques can either outperform the traditional ones or provide them with extra forecast information. In particular, based on the Granger-Newbold test, it appears that wavelets may be a promising new technique.

Original language	English
Pages (from-to)	80-89
Number of pages	10
Journal	Resources Policy
Volume	32
Issue number	1-2
DOIs	https://doi.org/10.1016/j.resourpol.2007.06.002
State	Published - Mar 2007

Keywords

Forecasting
Support vector machines
Wavelets

Access to Document

10.1016/j.resourpol.2007.06.002

Cite this

@article{e12ba44a332c409bb3f4259a44eae7af,

title = "Wavelet- and SVM-based forecasts: An analysis of the U.S. metal and materials manufacturing industry",

abstract = "This article compares four non-linear forecasting methods: multiplicative seasonal ARIMA, unobserved components (UC), wavelet-based and support vector machines (SVM). Whereas the first two methods are well known in the time series field, the other two rely on recently developed mathematical techniques. Based on forecasting accuracy and encompassing tests applied to shipments data of the U.S. metal and material manufacturing industry for 1958-2000, we conclude that that these two novel forecast techniques can either outperform the traditional ones or provide them with extra forecast information. In particular, based on the Granger-Newbold test, it appears that wavelets may be a promising new technique.",

keywords = "Forecasting, Support vector machines, Wavelets",

author = "Viviana Fernandez",

note = "Funding Information: Financial support from an institutional grant of the Hewlett Foundation to CEA and from FONDECYT Grant no. 1070762 is greatly acknowledged. This article was partially written at the Institute for International Integration Studies (IIIS), Trinity College, Dublin, while the author held a Visiting Research Fellowship during January–March 2006. All remaining errors are of the author.",

year = "2007",

month = mar,

doi = "10.1016/j.resourpol.2007.06.002",

language = "English",

volume = "32",

pages = "80--89",

journal = "Resources Policy",

issn = "0301-4207",

publisher = "Elsevier Ltd.",

number = "1-2",

}

TY - JOUR

T1 - Wavelet- and SVM-based forecasts

T2 - An analysis of the U.S. metal and materials manufacturing industry

AU - Fernandez, Viviana

N1 - Funding Information: Financial support from an institutional grant of the Hewlett Foundation to CEA and from FONDECYT Grant no. 1070762 is greatly acknowledged. This article was partially written at the Institute for International Integration Studies (IIIS), Trinity College, Dublin, while the author held a Visiting Research Fellowship during January–March 2006. All remaining errors are of the author.

PY - 2007/3

Y1 - 2007/3

N2 - This article compares four non-linear forecasting methods: multiplicative seasonal ARIMA, unobserved components (UC), wavelet-based and support vector machines (SVM). Whereas the first two methods are well known in the time series field, the other two rely on recently developed mathematical techniques. Based on forecasting accuracy and encompassing tests applied to shipments data of the U.S. metal and material manufacturing industry for 1958-2000, we conclude that that these two novel forecast techniques can either outperform the traditional ones or provide them with extra forecast information. In particular, based on the Granger-Newbold test, it appears that wavelets may be a promising new technique.

AB - This article compares four non-linear forecasting methods: multiplicative seasonal ARIMA, unobserved components (UC), wavelet-based and support vector machines (SVM). Whereas the first two methods are well known in the time series field, the other two rely on recently developed mathematical techniques. Based on forecasting accuracy and encompassing tests applied to shipments data of the U.S. metal and material manufacturing industry for 1958-2000, we conclude that that these two novel forecast techniques can either outperform the traditional ones or provide them with extra forecast information. In particular, based on the Granger-Newbold test, it appears that wavelets may be a promising new technique.

KW - Forecasting

KW - Support vector machines

KW - Wavelets

UR - http://www.scopus.com/inward/record.url?scp=34547525138&partnerID=8YFLogxK

U2 - 10.1016/j.resourpol.2007.06.002

DO - 10.1016/j.resourpol.2007.06.002

M3 - Article

AN - SCOPUS:34547525138

SN - 0301-4207

VL - 32

SP - 80

EP - 89

JO - Resources Policy

JF - Resources Policy

IS - 1-2

ER -

Wavelet- and SVM-based forecasts: An analysis of the U.S. metal and materials manufacturing industry

Abstract

Keywords

Access to Document

Fingerprint

Cite this