Publicación:
A novel feature engineering approach for high-frequency financial data

Vista sencilla de ítem
dc.contributor.authorMantilla, Pablo
dc.contributor.authorDormido Canto, Sebastián
dc.date.accessioned2024-05-20T11:38:20Z
dc.date.available2024-05-20T11:38:20Z
dc.date.issued2023-10
dc.description.abstractFeature engineering for high-frequency financial data based on constructing dynamic data subsets, defined by time intervals in which high-frequency trends occur, is proposed. These intervals are obtained through time series segmentation. This methodology allows us to extract and analyze variables by intraday trends as well as to feed artificial intelligence models to forecast response variables in future trends. Furthermore, to show how to use this feature engineering, this methodology is applied to estimate high-frequency volatility, duration and direction linked to future intraday trends, developing multiclass classification models based on the machine learning method extreme gradient boosting. Experimentation was conducted using high-frequency financial data from the Brazil Stock Exchange, corresponding to 206 trading days related to 20 listed assets from this financial market.en
dc.description.versionversión final
dc.identifier.doihttp://doi.org/10.1016/j.engappai.2023.106705
dc.identifier.issn0952-1976
dc.identifier.urihttps://hdl.handle.net/20.500.14468/12347
dc.journal.titleEngineering Applications of Artificial Intelligence
dc.journal.volume125
dc.language.isoen
dc.publisherElsevier
dc.relation.centerE.T.S. de Ingeniería Informática
dc.relation.departmentInformática y Automática
dc.rightsinfo:eu-repo/semantics/embargoedAccess
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0
dc.subject.keywordsArtificial intelligence in finance
dc.subject.keywordsHigh-frequency financial data
dc.subject.keywordsTime series segmentation
dc.subject.keywordsIntraday volatility
dc.subject.keywordsDirectional forecasting
dc.titleA novel feature engineering approach for high-frequency financial dataes
dc.typejournal articleen
dc.typeartículoes
dspace.entity.typePublication
relation.isAuthorOfPublicationf5f57d8a-f3c0-40a1-a93c-80d6237a2bcb
relation.isAuthorOfPublication.latestForDiscoveryf5f57d8a-f3c0-40a1-a93c-80d6237a2bcb
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
n02_Dormido_Canto_Sebastian_A_Novel_Feature.pdf
Tamaño:
759.79 KB
Formato:
Adobe Portable Document Format
Descargar
Colecciones
Artículos y papers