Autoencoder-enhanced clustering: a dimensionality reduction approach to financial time series

dc.contributor.authorGonzález Cortés, Daniel
dc.contributor.authorOnieva Caracuel, Enrique
dc.contributor.authorPastor López, Iker
dc.contributor.authorTrinchera, Laura
dc.contributor.authorWu, Jian
dc.date.accessioned2025-05-20T13:26:53Z
dc.date.available2025-05-20T13:26:53Z
dc.date.issued2024-02-05
dc.date.updated2025-05-20T13:26:53Z
dc.description.abstractWhile Machine Learning significantly boosts the performance of predictive models, its efficacy varies across different data dimensions. It is essential to cluster time series data of similar characteristics, particularly in the financial sector. However, clustering financial time series data poses considerable challenges due to the market's inherent complexity and multidimensionality. To address these issues, our study introduces a novel clustering framework that leverages autoencoders for a compressed yet informative representation of financial time series. We rigorously evaluate our approach through multiple dimensionality reduction and clustering algorithms, applying it to key financial indices, including IBEX-35, CAC-40, DAX-30, S&P 500, and FTSE 100. Our findings consistently demonstrate that incorporating autoencoders significantly enhances the granularity and quality of clustering, effectively isolating distinct categories of financial time series. Our findings carry significant ramifications for the financial industry. By refining clustering methodologies, we set the stage for increasingly accurate financial predictive models, offering valuable insights for optimizing investment strategies and enhancing risk management.en
dc.description.sponsorshipThis was supported in part by the NEOMA Business School under Grant 416004. The work of Daniel González Cortés, Laura Trinchera, and Jian Wu was supported by the Data Science for Insight and Value Creation, Research Group of the AE AI, Data Science and Business, NEOMA Business School.en
dc.identifier.citationCortes, D. G., Onieva, E., Lopez, I. P., Trinchera, L., & Wu, J. (2024). Autoencoder-enhanced clustering: a dimensionality reduction approach to financial time series. IEEE Access, 12, 16999-17009. https://doi.org/10.1109/ACCESS.2024.3359413
dc.identifier.doi10.1109/ACCESS.2024.3359413
dc.identifier.eissn2169-3536
dc.identifier.urihttps://hdl.handle.net/20.500.14454/2782
dc.language.isoeng
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.rights© 2024 The Authors
dc.subject.otherClustering methods
dc.subject.otherData compression
dc.subject.otherFinancial data processing
dc.subject.otherNeural network applications
dc.subject.otherTime series
dc.titleAutoencoder-enhanced clustering: a dimensionality reduction approach to financial time seriesen
dc.typejournal article
dcterms.accessRightsopen access
oaire.citation.endPage17009
oaire.citation.startPage16999
oaire.citation.titleIEEE Access
oaire.citation.volume12
oaire.licenseConditionhttps://creativecommons.org/licenses/by-nc-nd/4.0/
oaire.versionVoR
Archivos
Bloque original
Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
gonzalez_autoencoder_2024.pdf
Tamaño:
887.45 KB
Formato:
Adobe Portable Document Format
Colecciones