Cryptocurrency price projection based on Tweets using LSTM

Authors

  • Andrés Regal Universidad del Pacífico
  • Juandiego Morzán Universidad del Pacífico
  • Carlos Fabbri Universidad del Pacífico
  • Gonzalo Herrera Universidad del Pacífico
  • Gabriela Yaulli Universidad del Pacífico
  • Andrea Palomino Universidad del Pacífico
  • Claudia Gil Universidad del Pacífico

Keywords:

Cryptocurrencies, Twitter, LSTM

Abstract

The modeling and prediction of time series is essential for financial optimization. This study analyzes how social media posts can capture investor expectations and affect the value of cryptocurrencies. A Long Short Term Memory (LSTM) model is proposed to forecast daily market performance based on two components: cryptocurrency data and social media interactions (tweets). The model achieved a Mean Absolute Percentage Error of 34.92%, indicating the need for new Natural Language Processing (NLP) techniques to improve the prediction.

 

Downloads

Download data is not yet available.

Author Biographies

Andrés Regal, Universidad del Pacífico

Universidad del Pacífico. Facultad de Ingeniería

Juandiego Morzán, Universidad del Pacífico

Universidad del Pacífico. Facultad de Ingeniería

Carlos Fabbri, Universidad del Pacífico

Universidad del Pacífico. Facultad de Ingeniería

Gonzalo Herrera, Universidad del Pacífico

Universidad del Pacífico. Facultad de Ingeniería

Gabriela Yaulli, Universidad del Pacífico

Universidad del Pacífico. Facultad de Ingeniería

Andrea Palomino, Universidad del Pacífico

Universidad del Pacífico. Facultad de Ingeniería

Claudia Gil, Universidad del Pacífico

Universidad del Pacífico. Facultad de Ingeniería

Downloads

Published

2024-12-20

How to Cite

[1]
A. Regal, “Cryptocurrency price projection based on Tweets using LSTM”, Ingeniare, Rev. chil. ing., vol. 27, no. 4, Dec. 2024.

Issue

Vol. 27 No. 4 (2019): Volumen 27 Issue 4

Section

Articulos

License

Copyright (c) 2024 Revista Ingeniare

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors retain copyright of their work and grant the journal the right of first publication under the Creative Commons CC-BY Attribution License, which permits unrestricted use, distribution, and reproduction provided the original authorship and the journal’s first publication are acknowledged.