Una aplicación de redes neuronales artificiales para el pronostico de los rendimientos de la serie de Ecopetrol
Fecha
2021-01-20Registro en:
Garcia Ríos, D. A. (2020). Una aplicación de redes neuronales artificiales para el pronostico de los rendimientos de la serie de Ecopetrol. [Tesis de Pregrado, Universidad Santo Tomás Colombia]. Repositorio Institucional
reponame:Repositorio Institucional Universidad Santo Tomás
instname:Universidad Santo Tomás
Autor
Garcia Rios, Duvan Alejandro
Institución
Resumen
This work proposes a model based on recurrent neural networks (RNN) to forecast the performance of Ecopetrol, which is one of the most successful actions in the country. Various configurations of RNN are studied, including as input variables the representative market rate (TRM), euro (EUR), closing price of the respective share to estimate and oil prices (Brent and WTI). A part of the data is taken as training and the rest for prediction, finally to contrast the obtained results, an EGARCH model is fitted