Powered by OpenAIRE graph
Found an issue? Give us feedback
addClaim

Regresión en Series Temporales usando Aprendizaje Profundo

Authors: Couros García, Marcos;

Regresión en Series Temporales usando Aprendizaje Profundo

Abstract

El objetivo de este trabajo fin de grado (TFG) consiste en evaluar la predicción de series temporales mediante distintas técnicas basadas en aprendizaje profundo o Deep Learning ,y realizar una comparación con modelos clásicos como AR, MA, ARMA, ARIMA o SARIMA y con modelos basados en aprendizaje automático1. Desde que se presentó el anteproyecto de este TFG han irrumpido con fuerza dentro del Aprendizaje Profundo los Modelos Largos de Lenguaje (LLM en inglés) como chatGPT y variantes. Inicialmente no se contemplaba explorar el uso de modelos basados en la generación de lenguaje para la predicción de series temporales, pero dada la actualidad de este tipo de modelos haremos también una exploración inicial para ver el comportamiento de modelos de uso general, estando la creación de modelos específicos de LLM fuera del alcance de este TFG entre otras cosas debido al alto coste computacional que requiere este tipo de modelos. Un uso específico de modelos basados en GPT al sector financiero podemos encontrarlo en empresas como Bloomberg, con BloombergGPT 2.

Keywords

120317 Informática

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Upload OA version
Are you the author of this publication? Upload your Open Access version to Zenodo!
It’s fast and easy, just two clicks!