Home > Research > Publications & Outputs > Optimizing Theta model for monthly data
View graph of relations

Optimizing Theta model for monthly data

Research output: Contribution to conference - Without ISBN/ISSN Conference paper

Published

Standard

Optimizing Theta model for monthly data. / Petropoulos, Fotios; Nikolopoulos, Konstantinos.

2013. Paper presented at ICAART 2013 5th International Conference on Agents and Artificial Intelligence, Barcelona, Spain.

Research output: Contribution to conference - Without ISBN/ISSN Conference paper

Harvard

Petropoulos, F & Nikolopoulos, K 2013, 'Optimizing Theta model for monthly data', Paper presented at ICAART 2013 5th International Conference on Agents and Artificial Intelligence, Barcelona, Spain, 15/02/13 - 18/02/13.

APA

Petropoulos, F., & Nikolopoulos, K. (2013). Optimizing Theta model for monthly data. Paper presented at ICAART 2013 5th International Conference on Agents and Artificial Intelligence, Barcelona, Spain.

Vancouver

Petropoulos F, Nikolopoulos K. Optimizing Theta model for monthly data. 2013. Paper presented at ICAART 2013 5th International Conference on Agents and Artificial Intelligence, Barcelona, Spain.

Author

Petropoulos, Fotios ; Nikolopoulos, Konstantinos. / Optimizing Theta model for monthly data. Paper presented at ICAART 2013 5th International Conference on Agents and Artificial Intelligence, Barcelona, Spain.6 p.

Bibtex

@conference{d29df456968f4f16a3bfe0a196df96a4,
title = "Optimizing Theta model for monthly data",
abstract = "Forecasting accuracy and performance of extrapolation techniques has always been of major importance for both researchers and practitioners. Towards this direction, many forecasting competitions have conducted over the years, in order to provide solid performance measurement frameworks for new methods. The Theta model outperformed all other participants during the largest up-to-date competition (M3-competition). The model{\textquoteright}s performance is based to the a-priori decomposition of the original series into two separate lines, which contain specific amount of information regarding the short-term and long-term behavior of the data. The current research investigates possible modifications on the original Theta model, aiming to the development of an optimized version of the model specifically for the monthly data. The proposed adjustments refer to better estimation of the seasonal component, extension of the decomposition feature of the original model and better optimization procedures for the smoothing parameter. The optimized model was tested for its efficiency in a large data set containing more than 20,000 empirical series, displaying improved performance ability when monthly data are considered.",
keywords = "Forecasting Accuracy, Competitions, Theta Model, Seasonality, Time Series",
author = "Fotios Petropoulos and Konstantinos Nikolopoulos",
year = "2013",
language = "English",
note = "ICAART 2013 5th International Conference on Agents and Artificial Intelligence ; Conference date: 15-02-2013 Through 18-02-2013",

}

RIS

TY - CONF

T1 - Optimizing Theta model for monthly data

AU - Petropoulos, Fotios

AU - Nikolopoulos, Konstantinos

PY - 2013

Y1 - 2013

N2 - Forecasting accuracy and performance of extrapolation techniques has always been of major importance for both researchers and practitioners. Towards this direction, many forecasting competitions have conducted over the years, in order to provide solid performance measurement frameworks for new methods. The Theta model outperformed all other participants during the largest up-to-date competition (M3-competition). The model’s performance is based to the a-priori decomposition of the original series into two separate lines, which contain specific amount of information regarding the short-term and long-term behavior of the data. The current research investigates possible modifications on the original Theta model, aiming to the development of an optimized version of the model specifically for the monthly data. The proposed adjustments refer to better estimation of the seasonal component, extension of the decomposition feature of the original model and better optimization procedures for the smoothing parameter. The optimized model was tested for its efficiency in a large data set containing more than 20,000 empirical series, displaying improved performance ability when monthly data are considered.

AB - Forecasting accuracy and performance of extrapolation techniques has always been of major importance for both researchers and practitioners. Towards this direction, many forecasting competitions have conducted over the years, in order to provide solid performance measurement frameworks for new methods. The Theta model outperformed all other participants during the largest up-to-date competition (M3-competition). The model’s performance is based to the a-priori decomposition of the original series into two separate lines, which contain specific amount of information regarding the short-term and long-term behavior of the data. The current research investigates possible modifications on the original Theta model, aiming to the development of an optimized version of the model specifically for the monthly data. The proposed adjustments refer to better estimation of the seasonal component, extension of the decomposition feature of the original model and better optimization procedures for the smoothing parameter. The optimized model was tested for its efficiency in a large data set containing more than 20,000 empirical series, displaying improved performance ability when monthly data are considered.

KW - Forecasting Accuracy

KW - Competitions

KW - Theta Model

KW - Seasonality

KW - Time Series

M3 - Conference paper

T2 - ICAART 2013 5th International Conference on Agents and Artificial Intelligence

Y2 - 15 February 2013 through 18 February 2013

ER -