Construcción de modelos de predicción de activos financieros
Construcción de modelos de predicción de activos financieros
[Resumen]: En las últimas décadas, el aprendizaje automático ha tomado gran protagonismo, capturando la atención del público en general. El objeto de este trabajo radica en comparar diversos modelos de predicción de activos financieros, tales como las redes neuronales recurrentes (LSTM), random forest, regresión lineal y SVR. El caso de estudio será la cotización semanal al cierre de la acción SAN.MC, mediante este se buscará dar con un modelo que sea considerado óptimo para guiar a un individuo que desea conocer la posible evolución del precio de una acción que posee en cartera, sin contar con conocimientos de análisis técnico y fundamental.
[Abstract]: In recent decades, machine learning has gained significant importance, capturing the attention of the public. The purpose of this project is to compare various models for predicting financial assets, such as recurrent neural networks (LSTM), random forest, linear regression, and SVR. The case study will focus on the weekly closing price of the SAN.MC stock. The aim is to find an optimal model that can guide individuals who wish to understand the potential evolution of a stock's price in their portfolio, without requiring knowledge of technical and fundamental analysis.
Traballo fin de mestrado (UDC.ECO). Banca e finanzas. Curso 2022/2023
- University of A Coruña Spain
SVR, SVM, Regression model, MAPE, Price, Redes neuronales recurrentes, MAE, R2, RMSE, Aprendizaje automático, MSE, Ensemble model, Recurrent neural networks, Machine learning, Cotización, Modelo de regresión, LSTM, Precio, Python, Random forest, Modelo de ensamble
SVR, SVM, Regression model, MAPE, Price, Redes neuronales recurrentes, MAE, R2, RMSE, Aprendizaje automático, MSE, Ensemble model, Recurrent neural networks, Machine learning, Cotización, Modelo de regresión, LSTM, Precio, Python, Random forest, Modelo de ensamble
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
Citations provided by BIP!Popularity provided by BIP!