Futures Quantitative Investment with Heterogeneous Continual Graph Neural Network

This study aims to address the challenges of futures price prediction in high-frequency trading (HFT) by proposing a continuous learning factor predictor based on graph neural networks. The model integrates multi-factor pricing theories with real-time market dynamics, effectively bypassing the limit...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hu, Min, Tan, Zhizhong, Liu, Bin, Yin, Guosheng
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Hu, Min
Tan, Zhizhong
Liu, Bin
Yin, Guosheng
description This study aims to address the challenges of futures price prediction in high-frequency trading (HFT) by proposing a continuous learning factor predictor based on graph neural networks. The model integrates multi-factor pricing theories with real-time market dynamics, effectively bypassing the limitations of existing methods that lack financial theory guidance and ignore various trend signals and their interactions. We propose three heterogeneous tasks, including price moving average regression, price gap regression and change-point detection to trace the short-, intermediate-, and long-term trend factors present in the data. In addition, this study also considers the cross-sectional correlation characteristics of future contracts, where prices of different futures often show strong dynamic correlations. Each variable (future contract) depends not only on its historical values (temporal) but also on the observation of other variables (cross-sectional). To capture these dynamic relationships more accurately, we resort to the spatio-temporal graph neural network (STGNN) to enhance the predictive power of the model. The model employs a continuous learning strategy to simultaneously consider these tasks (factors). Additionally, due to the heterogeneity of the tasks, we propose to calculate parameter importance with mutual information between original observations and the extracted features to mitigate the catastrophic forgetting (CF) problem. Empirical tests on 49 commodity futures in China's futures market demonstrate that the proposed model outperforms other state-of-the-art models in terms of prediction accuracy. Not only does this research promote the integration of financial theory and deep learning, but it also provides a scientific basis for actual trading decisions.
doi_str_mv 10.48550/arxiv.2303.16532
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2303_16532</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2303_16532</sourcerecordid><originalsourceid>FETCH-LOGICAL-a672-7a190b1360da6ac20b243db215cacc5b783000c9cb6322b57bae39982b290a223</originalsourceid><addsrcrecordid>eNotz81KAzEUBeBsXEj1AVyZF5gxc9NkJksZ7A-USqH74Sa92mCbKZlkqm9vrV0dDhwOfIw9VaKcNkqJF4zffixBCllWWkm4Z5tZTjnSwDcZQ_IJkx-JL8NIQzpSSPzs054vKFHsPylQnwfe9pdlyHjg84inPV9TjpeypnTu49cDu_vAw0CPt5yw7ext2y6K1ft82b6uCtQ1FDVWRthKarFDjQ6EhancWaiUQ-eUrRsphHDGWS0BrKotkjSmAQtGIICcsOf_26upO0V_xPjT_dm6q03-AkraSok</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Futures Quantitative Investment with Heterogeneous Continual Graph Neural Network</title><source>arXiv.org</source><creator>Hu, Min ; Tan, Zhizhong ; Liu, Bin ; Yin, Guosheng</creator><creatorcontrib>Hu, Min ; Tan, Zhizhong ; Liu, Bin ; Yin, Guosheng</creatorcontrib><description>This study aims to address the challenges of futures price prediction in high-frequency trading (HFT) by proposing a continuous learning factor predictor based on graph neural networks. The model integrates multi-factor pricing theories with real-time market dynamics, effectively bypassing the limitations of existing methods that lack financial theory guidance and ignore various trend signals and their interactions. We propose three heterogeneous tasks, including price moving average regression, price gap regression and change-point detection to trace the short-, intermediate-, and long-term trend factors present in the data. In addition, this study also considers the cross-sectional correlation characteristics of future contracts, where prices of different futures often show strong dynamic correlations. Each variable (future contract) depends not only on its historical values (temporal) but also on the observation of other variables (cross-sectional). To capture these dynamic relationships more accurately, we resort to the spatio-temporal graph neural network (STGNN) to enhance the predictive power of the model. The model employs a continuous learning strategy to simultaneously consider these tasks (factors). Additionally, due to the heterogeneity of the tasks, we propose to calculate parameter importance with mutual information between original observations and the extracted features to mitigate the catastrophic forgetting (CF) problem. Empirical tests on 49 commodity futures in China's futures market demonstrate that the proposed model outperforms other state-of-the-art models in terms of prediction accuracy. Not only does this research promote the integration of financial theory and deep learning, but it also provides a scientific basis for actual trading decisions.</description><identifier>DOI: 10.48550/arxiv.2303.16532</identifier><language>eng</language><subject>Computer Science - Learning ; Quantitative Finance - Statistical Finance ; Statistics - Applications</subject><creationdate>2023-03</creationdate><rights>http://creativecommons.org/licenses/by-nc-nd/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2303.16532$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2303.16532$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Hu, Min</creatorcontrib><creatorcontrib>Tan, Zhizhong</creatorcontrib><creatorcontrib>Liu, Bin</creatorcontrib><creatorcontrib>Yin, Guosheng</creatorcontrib><title>Futures Quantitative Investment with Heterogeneous Continual Graph Neural Network</title><description>This study aims to address the challenges of futures price prediction in high-frequency trading (HFT) by proposing a continuous learning factor predictor based on graph neural networks. The model integrates multi-factor pricing theories with real-time market dynamics, effectively bypassing the limitations of existing methods that lack financial theory guidance and ignore various trend signals and their interactions. We propose three heterogeneous tasks, including price moving average regression, price gap regression and change-point detection to trace the short-, intermediate-, and long-term trend factors present in the data. In addition, this study also considers the cross-sectional correlation characteristics of future contracts, where prices of different futures often show strong dynamic correlations. Each variable (future contract) depends not only on its historical values (temporal) but also on the observation of other variables (cross-sectional). To capture these dynamic relationships more accurately, we resort to the spatio-temporal graph neural network (STGNN) to enhance the predictive power of the model. The model employs a continuous learning strategy to simultaneously consider these tasks (factors). Additionally, due to the heterogeneity of the tasks, we propose to calculate parameter importance with mutual information between original observations and the extracted features to mitigate the catastrophic forgetting (CF) problem. Empirical tests on 49 commodity futures in China's futures market demonstrate that the proposed model outperforms other state-of-the-art models in terms of prediction accuracy. Not only does this research promote the integration of financial theory and deep learning, but it also provides a scientific basis for actual trading decisions.</description><subject>Computer Science - Learning</subject><subject>Quantitative Finance - Statistical Finance</subject><subject>Statistics - Applications</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz81KAzEUBeBsXEj1AVyZF5gxc9NkJksZ7A-USqH74Sa92mCbKZlkqm9vrV0dDhwOfIw9VaKcNkqJF4zffixBCllWWkm4Z5tZTjnSwDcZQ_IJkx-JL8NIQzpSSPzs054vKFHsPylQnwfe9pdlyHjg84inPV9TjpeypnTu49cDu_vAw0CPt5yw7ext2y6K1ft82b6uCtQ1FDVWRthKarFDjQ6EhancWaiUQ-eUrRsphHDGWS0BrKotkjSmAQtGIICcsOf_26upO0V_xPjT_dm6q03-AkraSok</recordid><startdate>20230329</startdate><enddate>20230329</enddate><creator>Hu, Min</creator><creator>Tan, Zhizhong</creator><creator>Liu, Bin</creator><creator>Yin, Guosheng</creator><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20230329</creationdate><title>Futures Quantitative Investment with Heterogeneous Continual Graph Neural Network</title><author>Hu, Min ; Tan, Zhizhong ; Liu, Bin ; Yin, Guosheng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a672-7a190b1360da6ac20b243db215cacc5b783000c9cb6322b57bae39982b290a223</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Learning</topic><topic>Quantitative Finance - Statistical Finance</topic><topic>Statistics - Applications</topic><toplevel>online_resources</toplevel><creatorcontrib>Hu, Min</creatorcontrib><creatorcontrib>Tan, Zhizhong</creatorcontrib><creatorcontrib>Liu, Bin</creatorcontrib><creatorcontrib>Yin, Guosheng</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Hu, Min</au><au>Tan, Zhizhong</au><au>Liu, Bin</au><au>Yin, Guosheng</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Futures Quantitative Investment with Heterogeneous Continual Graph Neural Network</atitle><date>2023-03-29</date><risdate>2023</risdate><abstract>This study aims to address the challenges of futures price prediction in high-frequency trading (HFT) by proposing a continuous learning factor predictor based on graph neural networks. The model integrates multi-factor pricing theories with real-time market dynamics, effectively bypassing the limitations of existing methods that lack financial theory guidance and ignore various trend signals and their interactions. We propose three heterogeneous tasks, including price moving average regression, price gap regression and change-point detection to trace the short-, intermediate-, and long-term trend factors present in the data. In addition, this study also considers the cross-sectional correlation characteristics of future contracts, where prices of different futures often show strong dynamic correlations. Each variable (future contract) depends not only on its historical values (temporal) but also on the observation of other variables (cross-sectional). To capture these dynamic relationships more accurately, we resort to the spatio-temporal graph neural network (STGNN) to enhance the predictive power of the model. The model employs a continuous learning strategy to simultaneously consider these tasks (factors). Additionally, due to the heterogeneity of the tasks, we propose to calculate parameter importance with mutual information between original observations and the extracted features to mitigate the catastrophic forgetting (CF) problem. Empirical tests on 49 commodity futures in China's futures market demonstrate that the proposed model outperforms other state-of-the-art models in terms of prediction accuracy. Not only does this research promote the integration of financial theory and deep learning, but it also provides a scientific basis for actual trading decisions.</abstract><doi>10.48550/arxiv.2303.16532</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2303.16532
ispartof
issn
language eng
recordid cdi_arxiv_primary_2303_16532
source arXiv.org
subjects Computer Science - Learning
Quantitative Finance - Statistical Finance
Statistics - Applications
title Futures Quantitative Investment with Heterogeneous Continual Graph Neural Network
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-03T10%3A53%3A08IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Futures%20Quantitative%20Investment%20with%20Heterogeneous%20Continual%20Graph%20Neural%20Network&rft.au=Hu,%20Min&rft.date=2023-03-29&rft_id=info:doi/10.48550/arxiv.2303.16532&rft_dat=%3Carxiv_GOX%3E2303_16532%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true