Prevendo o volume de moedas alternativas ao Bitcoin com machine learning e o impacto dessa previsão no volume do Bitcoin

One of the great challenges of analyzing cryptocurrencies, especially Bitcoin and its alternative currencies (Altcoins), is price fluctuation, which makes it difficult to estimate whether this asset is in good shape buy or sell. This work aims to use the volume indicator and quotations of 4 other al...

ver descrição completa

Autor principal: Tenório, Anderson da Silva
Formato: Trabalho de Conclusão de Curso (Graduação)
Idioma: Português
Publicado em: Universidade Tecnológica Federal do Paraná 2023
Assuntos:
Acesso em linha: http://repositorio.utfpr.edu.br/jspui/handle/1/30641
Tags: Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!
Resumo: One of the great challenges of analyzing cryptocurrencies, especially Bitcoin and its alternative currencies (Altcoins), is price fluctuation, which makes it difficult to estimate whether this asset is in good shape buy or sell. This work aims to use the volume indicator and quotations of 4 other alternative cryptocurrencies to Bitcoin (Altcoins) in the short term and apply the Long Short-Term Memory (LSTM) method Memory). The results aim to discover the future volumetry behavior of Bitcoin. Forecast values were obtained with root mean square error (RMSE) equal to 39.62 for Altcoins and 355.60 for Bitcoin, values which should be adjusted closer to zero to be qualitatively better adjusted.