Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Recolector de Cienci...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
BULERIA
Bachelor thesis . 2022
Data sources: BULERIA
BULERIA
Bachelor thesis
Data sources: BULERIA
versions View all 3 versions
addClaim

Predicción del precio de bitcoin mediante aprendizaje profundo

Bitcoin price forecasting through deep learning
Authors: Díez Gutiérrez, Carlos;

Predicción del precio de bitcoin mediante aprendizaje profundo

Abstract

[ES] Predecir el precio de Bitcoin y en general, cualquier activo financiero es un problema que hasta el momento no tiene solución debido a su alta volatilidad y aleatoriedad. Este trabajo se centrará en descubrir cuáles son los mejores enfoques para realizar predicciones de la manera más precisa y robusta posible utilizando tecnologías basadas en el aprendizaje profundo. Por tanto, se analizarán los precios de Bitcoin y se le aplicarán distintos algoritmos para adaptar la serie temporal a un problema supervisado. Después de realizar el entrenamiento, se compararán diferentes enfoques en los que se tendrá en cuenta el tipo de estacionariedad de la serie temporal, la dimensión de la serie temporal (univariable o multivariable), el tipo de escalado y el tipo de modelo de aprendizaje profundo junto con sus distintos hiperparámetros. Tras realizar estas comparaciones, se podrá conocer cuál es el mejor enfoque para predecir de forma precisa el precio de bitcoin.

[EN] Predicting the price of Bitcoin and, in general, any financial asset is a problem that so far has no solution due to its high volatility and randomness. This work will focus on discovering the best approaches to make predictions as accurately and robustly as possible using deep learning-based technologies. Therefore, Bitcoin prices will be analysed and different algorithms will be applied to adapt the time series to a supervised problem. After training, different approaches will be compared, taking into account the type of stationarity of the time series, the dimension of the time series (univariate or multivariate), the type of scaling and the type of deep learning model together with its different hyperparameters. After making these comparisons, the best approach to accurately predict the price of bitcoin will be known.

Country
Spain
Related Organizations
Keywords

Cibernética, Informática, Series temporales, 1207.03 Cibernética, Aprendizaje profundo, 1206.01 Construcción de Algoritmos, Predicción, Estadística, Finanzas, 1209.14 Técnicas de Predicción Estadística, Aprendizaje automático

  • 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
Green