Autoregressive and neural network models: A comparative study with linearly lagged series

dc.contributor.author Kamalov, Firuz
dc.contributor.author Gurrib, Ikhlaas
dc.contributor.author Thabtah, Fadi
dc.date.accessioned 2021-12-29T10:21:12Z
dc.date.available 2021-12-29T10:21:12Z
dc.date.copyright © 2021
dc.date.issued 2021-09-29
dc.description This conference paper is not available at CUD collection. The version of scholarly record of this conference paper is published in2021 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies, 3ICT 2021 (2021), available online at: https://doi.org/10.1109/3ICT53449.2021.9581812 en_US
dc.description.abstract Time series analysis such as stock price forecasting is an important part of financial research. In this regard, autoregressive (AR) and neural network (NN) models offer contrasting approaches to time series modeling. Although AR models remain widely used, NN models and their variant long short-term memory (LSTM) networks have grown in popularity. In this paper, we compare the performance of AR, NN, and LSTM models in forecasting linearly lagged time series. To test the models we carry out extensive numerical experiments based on simulated data. The results of the experiments reveal that despite the inherent advantage of AR models in modeling linearly lagged data, NN models perform just as well, if not better, than AR models. Furthermore, the NN models outperform LSTMs on the same data. We find that a simple multi-layer perceptron can achieve highly accurate out of sample forecasts. The study shows that NN models perform well even in the case of linearly lagged time series. © 2021 IEEE. en_US
dc.identifier.citation Kamalov, F., Gurrib, I., & Thabtah, F. (2021). Autoregressive and neural network models: A comparative study with linearly lagged series. Paper presented at the 2021 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies, 3ICT 2021, 175-180. https://doi.org/10.1109/3ICT53449.2021.9581812 en_US
dc.identifier.isbn 978-166544032-5
dc.identifier.uri https://doi.org/10.1109/3ICT53449.2021.9581812
dc.identifier.uri http://hdl.handle.net/20.500.12519/485
dc.language.iso en en_US
dc.publisher Institute of Electrical and Electronics Engineers Inc. en_US
dc.relation Authors Affiliations : Kamalov, F., Canadian University Dubai, Department of Electrical Engineering, Dubai, United Arab Emirates; Gurrib, I., Canadian University Dubai, Department of Finance, Dubai, United Arab Emirates; Thabtah, F., School of Digital Technologies, Manukau Institute of Technology, Manukau, New Zealand
dc.relation.ispartofseries 2021 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies, 3ICT 2021;
dc.rights Permission to reuse abstract has been secured from Institute of Electrical and Electronics Engineers Inc.
dc.rights.holder Copyright : © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
dc.rights.uri https://www.ieee.org/publications/rights/rights-policies.html
dc.subject AR en_US
dc.subject ARIMA en_US
dc.subject forecast en_US
dc.subject LSTM en_US
dc.subject neural network en_US
dc.subject time series en_US
dc.title Autoregressive and neural network models: A comparative study with linearly lagged series en_US
dc.type Conference Paper en_US
Files
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.01 KB
Format:
Item-specific license agreed upon to submission
Description: