Several studies have applied genetic programming (GP)
to the task of forecasting with favourable results.
However, these studies, like those applying other
techniques, have assumed a static environment, making
them unsuitable for many real-world time series which
are generated by varying processes. This study
investigates the development of a new dynamic GP model
that is specifically tailored for forecasting in
nonstatic environments. This Dynamic Forecasting
Genetic Program (DyFor GP) model incorporates features
that allow it to adapt to changing environments
automatically as well as retain knowledge learned from
previously encountered environments. The DyFor GP model
is tested for forecasting efficacy on both simulated
and actual time series including the U.S. Gross
Domestic Product and Consumer Price Index Inflation.
Results show that the performance of the DyFor GP model
improves upon that of benchmark models for all
experiments. These findings highlight the DyFor GP's
potential as an adaptive, nonlinear model for
real-world forecasting applications and suggest further
investigations.
%0 Journal Article
%1 wagner:2007:tec
%A Wagner, Neal
%A Michalewicz, Zbigniew
%A Khouja, Moutaz
%A McGregor, Rob Roy
%D 2007
%J IEEE Transactions on Evolutionary Computation
%K Dynamic, adaptation, algorithms, forecasting, genetic parameter programming, series time
%N 4
%P 433--452
%R doi:10.1109/TEVC.2006.882430
%T Time Series Forecasting for Dynamic Environments: The
DyFor Genetic Program Model
%V 11
%X Several studies have applied genetic programming (GP)
to the task of forecasting with favourable results.
However, these studies, like those applying other
techniques, have assumed a static environment, making
them unsuitable for many real-world time series which
are generated by varying processes. This study
investigates the development of a new dynamic GP model
that is specifically tailored for forecasting in
nonstatic environments. This Dynamic Forecasting
Genetic Program (DyFor GP) model incorporates features
that allow it to adapt to changing environments
automatically as well as retain knowledge learned from
previously encountered environments. The DyFor GP model
is tested for forecasting efficacy on both simulated
and actual time series including the U.S. Gross
Domestic Product and Consumer Price Index Inflation.
Results show that the performance of the DyFor GP model
improves upon that of benchmark models for all
experiments. These findings highlight the DyFor GP's
potential as an adaptive, nonlinear model for
real-world forecasting applications and suggest further
investigations.
@article{wagner:2007:tec,
abstract = {Several studies have applied genetic programming (GP)
to the task of forecasting with favourable results.
However, these studies, like those applying other
techniques, have assumed a static environment, making
them unsuitable for many real-world time series which
are generated by varying processes. This study
investigates the development of a new dynamic GP model
that is specifically tailored for forecasting in
nonstatic environments. This Dynamic Forecasting
Genetic Program (DyFor GP) model incorporates features
that allow it to adapt to changing environments
automatically as well as retain knowledge learned from
previously encountered environments. The DyFor GP model
is tested for forecasting efficacy on both simulated
and actual time series including the U.S. Gross
Domestic Product and Consumer Price Index Inflation.
Results show that the performance of the DyFor GP model
improves upon that of benchmark models for all
experiments. These findings highlight the DyFor GP's
potential as an adaptive, nonlinear model for
real-world forecasting applications and suggest further
investigations.},
added-at = {2008-06-19T17:46:40.000+0200},
author = {Wagner, Neal and Michalewicz, Zbigniew and Khouja, Moutaz and McGregor, Rob Roy},
biburl = {https://www.bibsonomy.org/bibtex/2c986d885fd7e3c496801527777e3e732/brazovayeye},
doi = {doi:10.1109/TEVC.2006.882430},
interhash = {e42c35747aec1dfc80383ba8a95272ce},
intrahash = {c986d885fd7e3c496801527777e3e732},
issn = {1389-2576},
journal = {IEEE Transactions on Evolutionary Computation},
keywords = {Dynamic, adaptation, algorithms, forecasting, genetic parameter programming, series time},
month = {August},
number = 4,
pages = {433--452},
size = {20 pages},
timestamp = {2008-06-19T17:53:45.000+0200},
title = {Time Series Forecasting for Dynamic Environments: The
DyFor Genetic Program Model},
volume = 11,
year = 2007
}