Use this link to cite:
https://hdl.handle.net/2183/49561 Predicción de series temporales financieras mediante redes neuronales recurrentes y análisis de sentimiento de noticias bursátiles
Loading...
Identifiers
Publication date
Authors
Serantes Abal, Eloi
Advisors
Other responsabilities
Universidade da Coruña. Facultade de Informática
Journal Title
Bibliographic citation
Type of academic work
Academic degree
Abstract
[Resumen] Este Trabajo de Fin de Grado implementa un sistema de inversión algorítmica que combina Redes Neuronales Recurrentes con técnicas de Procesamiento del Lenguaje Natural para la predicción bursátil. El modelo integra el histórico de cotizaciones de un activo con el análisis de sentimiento extraído de noticias financieras, evaluando su rendimiento mediante un simulador de trading. El objetivo es superar las estrategias pasivas tradicionales, demostrando que la asimilación del contexto informativo permite al algoritmo gestionar el riesgo de forma activa, anticipar correcciones del mercado y mejorar la estabilidad de la cartera de inversión.
[Abstract] This Bachelor’s Thesis implements an algorithmic trading system that combines Recurrent Neural Networks with Natural Language Processing techniques for stock market prediction. The model integrates an asset’s historical price data with sentiment analysis extracted from financial news, evaluating its performance through a trading simulator. The objective is to outperform traditional passive strategies, demonstrating that assimilating the informational context allows the algorithm to actively manage risk, anticipate market corrections, and improve the stability of the investment portfolio.
[Abstract] This Bachelor’s Thesis implements an algorithmic trading system that combines Recurrent Neural Networks with Natural Language Processing techniques for stock market prediction. The model integrates an asset’s historical price data with sentiment analysis extracted from financial news, evaluating its performance through a trading simulator. The objective is to outperform traditional passive strategies, demonstrating that assimilating the informational context allows the algorithm to actively manage risk, anticipate market corrections, and improve the stability of the investment portfolio.
Description
Editor version
Rights
Attribution-NonCommercial-NoDerivatives 4.0 International








