Publication:
Incremental market behavior classification in presence of recurring concepts

Simple item page
dc.affiliation.dptoUC3M. Departamento de Informáticaes
dc.affiliation.grupoinvUC3M. Grupo de Investigación: Computación Evolutiva y Redes Neuronales (EVANNAI)es
dc.contributor.authorSuárez Cetrulo, Andrés L.
dc.contributor.authorCervantes Rovira, Alejandro
dc.contributor.authorQuintana, David
dc.contributor.funderMinisterio de Economía y Competitividad (España)es
dc.date.accessioned2022-06-07T08:48:24Z
dc.date.available2022-06-07T08:48:24Z
dc.date.issued2019-01-01
dc.description.abstractIn recent years, the problem of concept drift has gained importance in the financial domain. The succession of manias, panics and crashes have stressed the non-stationary nature and the likelihood of drastic structural or concept changes in the markets. Traditional systems are unable or slow to adapt to these changes. Ensemble-based systems are widely known for their good results predicting both cyclic and non-stationary data such as stock prices. In this work, we propose RCARF (Recurring Concepts Adaptive Random Forests), an ensemble tree-based online classifier that handles recurring concepts explicitly. The algorithm extends the capabilities of a version of Random Forest for evolving data streams, adding on top a mechanism to store and handle a shared collection of inactive trees, called concept history, which holds memories of the way market operators reacted in similar circumstances. This works in conjunction with a decision strategy that reacts to drift by replacing active trees with the best available alternative: either a previously stored tree from the concept history or a newly trained background tree. Both mechanisms are designed to provide fast reaction times and are thus applicable to high-frequency data. The experimental validation of the algorithm is based on the prediction of price movement directions one second ahead in the SPDR (Standard & Poor's Depositary Receipts) S&P 500 Exchange-Traded Fund. RCARF is benchmarked against other popular methods from the incremental online machine learning literature and is able to achieve competitive results.en
dc.description.sponsorshipThis research was funded by the Spanish Ministry of Economy and Competitiveness under grant number ENE2014-56126-C2-2-R.en
dc.identifier.bibliographicCitationSuárez-Cetrulo, A.L.; Cervantes, A.; Quintana, D. Incremental Market Behavior Classification in Presence of Recurring Concepts. Entropy 2019, 21, 25. https://doi.org/10.3390/e21010025en
dc.identifier.doihttps://doi.org/10.3390/e21010025
dc.identifier.issn1099-4300
dc.identifier.publicationfirstpage1
dc.identifier.publicationissue25
dc.identifier.publicationlastpage18
dc.identifier.publicationtitleEntropy (Entropy)en
dc.identifier.publicationvolume21
dc.identifier.urihttps://hdl.handle.net/10016/35010
dc.identifier.uxxiAR/0000023296
dc.language.isoeng
dc.publisherMDPIen
dc.relation.projectIDGobierno de España. ENE2014-56126-C2-2-Res
dc.rights© MDPI, 2019
dc.rightsAtribución 3.0 España
dc.rights.accessRightsopen accessen
dc.rights.urihttp://creativecommons.org/licenses/by/3.0/es/
dc.subject.ecienciaInformáticaes
dc.subject.otherensemble methodsen
dc.subject.otheradaptive classifiersen
dc.subject.otherrecurrent conceptsen
dc.subject.otherconcept driften
dc.subject.otherstock price direction predictionen
dc.titleIncremental market behavior classification in presence of recurring conceptsen
dc.typeresearch article*
dc.type.hasVersionVoR*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
incremental_E_2019.pdf
Size:
854.3 KB
Format:
Adobe Portable Document Format
Description:
Download
Collections
DI - GCERN - Artículos de revistas científicas