Home > Research > Publications & Outputs > Feature selection of autoregressive Neural Netw...

Research

Text available via DOI:

Keywords

View graph of relations

Feature selection of autoregressive Neural Network inputs for trend Time Series Forecasting

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

Feature selection of autoregressive Neural Network inputs for trend Time Series Forecasting. / Crone, Sven F.; Häger, Stephan.
2016 International Joint Conference on Neural Networks, IJCNN 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 1515-1522 7727378 (Proceedings of the International Joint Conference on Neural Networks; Vol. 2016-October).

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Crone, SF & Häger, S 2016, Feature selection of autoregressive Neural Network inputs for trend Time Series Forecasting. in 2016 International Joint Conference on Neural Networks, IJCNN 2016., 7727378, Proceedings of the International Joint Conference on Neural Networks, vol. 2016-October, Institute of Electrical and Electronics Engineers Inc., pp. 1515-1522, 2016 International Joint Conference on Neural Networks, IJCNN 2016, Vancouver, Canada, 24/07/16. https://doi.org/10.1109/IJCNN.2016.7727378

APA

Crone, S. F., & Häger, S. (2016). Feature selection of autoregressive Neural Network inputs for trend Time Series Forecasting. In 2016 International Joint Conference on Neural Networks, IJCNN 2016 (pp. 1515-1522). Article 7727378 (Proceedings of the International Joint Conference on Neural Networks; Vol. 2016-October). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.2016.7727378

Vancouver

Crone SF, Häger S. Feature selection of autoregressive Neural Network inputs for trend Time Series Forecasting. In 2016 International Joint Conference on Neural Networks, IJCNN 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 1515-1522. 7727378. (Proceedings of the International Joint Conference on Neural Networks). doi: 10.1109/IJCNN.2016.7727378

Author

Crone, Sven F. ; Häger, Stephan. / Feature selection of autoregressive Neural Network inputs for trend Time Series Forecasting. 2016 International Joint Conference on Neural Networks, IJCNN 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 1515-1522 (Proceedings of the International Joint Conference on Neural Networks).

Bibtex

@inproceedings{7cf47fdb19d5418eb82516072308cb0f,
title = "Feature selection of autoregressive Neural Network inputs for trend Time Series Forecasting",
abstract = "The capability of artificial Neural Networks to forecast time series with trends has been a topic of dispute. While selected research following Zhang and Qi has indicated that prior removal of trends is required for a Multilayer Perceptron (MLP), others provide evidence that Neural Networks are capable of forecasting trends without data preprocessing, either by choosing input-nodes employing an adequate autoregressive lag-structure of lagged realisations or by adding explanatory variables with trends. This paper proposes a novel variable selection methodology of autoregressive lags for trended time series with and without seasonality, and assesses its efficacy using the dataset of the International Time Series Forecasting Competition conducted at WCCI 2016. Our experiments indicate that MLPs are capable of forecasting different trend forms, but that more than a single lag-structure is required to do so, making the use of multiple input-lag variants and a robust model selection strategy necessary to achieve robust forecast accuracy.",
keywords = "Artificial neural networks, Forecasting, Seasonal time series, Structural breaks, Time series prediction, Trend time series",
author = "Crone, {Sven F.} and Stephan H{\"a}ger",
note = "Publisher Copyright: {\textcopyright} 2016 IEEE. Copyright: Copyright 2017 Elsevier B.V., All rights reserved.; 2016 International Joint Conference on Neural Networks, IJCNN 2016 ; Conference date: 24-07-2016 Through 29-07-2016",
year = "2016",
month = oct,
day = "31",
doi = "10.1109/IJCNN.2016.7727378",
language = "English",
series = "Proceedings of the International Joint Conference on Neural Networks",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1515--1522",
booktitle = "2016 International Joint Conference on Neural Networks, IJCNN 2016",

}

RIS

TY - GEN

T1 - Feature selection of autoregressive Neural Network inputs for trend Time Series Forecasting

AU - Crone, Sven F.

AU - Häger, Stephan

N1 - Publisher Copyright: © 2016 IEEE. Copyright: Copyright 2017 Elsevier B.V., All rights reserved.

PY - 2016/10/31

Y1 - 2016/10/31

N2 - The capability of artificial Neural Networks to forecast time series with trends has been a topic of dispute. While selected research following Zhang and Qi has indicated that prior removal of trends is required for a Multilayer Perceptron (MLP), others provide evidence that Neural Networks are capable of forecasting trends without data preprocessing, either by choosing input-nodes employing an adequate autoregressive lag-structure of lagged realisations or by adding explanatory variables with trends. This paper proposes a novel variable selection methodology of autoregressive lags for trended time series with and without seasonality, and assesses its efficacy using the dataset of the International Time Series Forecasting Competition conducted at WCCI 2016. Our experiments indicate that MLPs are capable of forecasting different trend forms, but that more than a single lag-structure is required to do so, making the use of multiple input-lag variants and a robust model selection strategy necessary to achieve robust forecast accuracy.

AB - The capability of artificial Neural Networks to forecast time series with trends has been a topic of dispute. While selected research following Zhang and Qi has indicated that prior removal of trends is required for a Multilayer Perceptron (MLP), others provide evidence that Neural Networks are capable of forecasting trends without data preprocessing, either by choosing input-nodes employing an adequate autoregressive lag-structure of lagged realisations or by adding explanatory variables with trends. This paper proposes a novel variable selection methodology of autoregressive lags for trended time series with and without seasonality, and assesses its efficacy using the dataset of the International Time Series Forecasting Competition conducted at WCCI 2016. Our experiments indicate that MLPs are capable of forecasting different trend forms, but that more than a single lag-structure is required to do so, making the use of multiple input-lag variants and a robust model selection strategy necessary to achieve robust forecast accuracy.

KW - Artificial neural networks

KW - Forecasting

KW - Seasonal time series

KW - Structural breaks

KW - Time series prediction

KW - Trend time series

UR - http://www.scopus.com/inward/record.url?scp=85007194199&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2016.7727378

DO - 10.1109/IJCNN.2016.7727378

M3 - Conference contribution/Paper

AN - SCOPUS:85007194199

T3 - Proceedings of the International Joint Conference on Neural Networks

SP - 1515

EP - 1522

BT - 2016 International Joint Conference on Neural Networks, IJCNN 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2016 International Joint Conference on Neural Networks, IJCNN 2016

Y2 - 24 July 2016 through 29 July 2016

ER -