Supervised temporal autoencoder for stock return time-series forecasting

Wong, SYK; Chan, JSK; Azizi, L; Xu, RYD

Supervised temporal autoencoder for stock return time-series forecasting

Wong, SYK Chan, JSK Azizi, L Xu, RYD

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: Proceedings - 2021 IEEE 45th Annual Computers, Software, and Applications Conference, COMPSAC 2021, 2021, 00, pp. 1735-1741
Issue Date:: 2021-07-01

Closed Access

	Filename	Description	Size
	Supervised_Temporal_Autoencoder_for_Stock_Return_Time-series_Forecasting.pdf	Published version	1.97 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Wong, SYK
dc.contributor.author	Chan, JSK
dc.contributor.author	Azizi, L
dc.contributor.author	Xu, RYD
dc.date	2021-07-12
dc.date.accessioned	2022-07-02T08:10:08Z
dc.date.available	2022-07-02T08:10:08Z
dc.date.issued	2021-07-01
dc.identifier.citation	Proceedings - 2021 IEEE 45th Annual Computers, Software, and Applications Conference, COMPSAC 2021, 2021, 00, pp. 1735-1741
dc.identifier.isbn	9781665424639
dc.identifier.issn	0730-3157
dc.identifier.uri	http://hdl.handle.net/10453/158529
dc.description.abstract	Financial markets are noisy learning environments. We propose an approach that regularizes the Temporal Convolutional Network using a supervised autoencoder, which we term the Supervised Temporal Autoencoder (STAE). We show that the addition of the auxiliary reconstruction task is beneficial to the primary supervised learning task in the context of stock return time-series forecasting. We also show that STAE is able to learn features directly from transformed price series, alleviating the need for handcrafted features. The autoencoder also improves interpretability as users can observe output of the decoder and inspect features retained by the network.
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	Proceedings - 2021 IEEE 45th Annual Computers, Software, and Applications Conference, COMPSAC 2021
dc.relation.ispartof	IEEE Annual Computers, Software, and Applications Conference
dc.relation.isbasedon	10.1109/COMPSAC51774.2021.00259
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Supervised temporal autoencoder for stock return time-series forecasting
dc.type	Conference Proceeding
utslib.citation.volume	00
utslib.location.activity	Madrid, Spain
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - INEXT - Innovation in IT Services and Applications
pubs.organisational-group	/University of Technology Sydney/Strength - GBDTC - Global Big Data Technologies
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2022-07-02T08:10:06Z
pubs.finish-date	2021-07-16
pubs.place-of-publication	Piscataway, USA
pubs.publication-status	Published
pubs.start-date	2021-07-12
pubs.volume	00
dc.location	Piscataway, USA

Abstract:

Financial markets are noisy learning environments. We propose an approach that regularizes the Temporal Convolutional Network using a supervised autoencoder, which we term the Supervised Temporal Autoencoder (STAE). We show that the addition of the auxiliary reconstruction task is beneficial to the primary supervised learning task in the context of stock return time-series forecasting. We also show that STAE is able to learn features directly from transformed price series, alleviating the need for handcrafted features. The autoencoder also improves interpretability as users can observe output of the decoder and inspect features retained by the network.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/158529