Published

2006-01-01

PREDICCIÓN DE SERIES TEMPORALES CON REDES NEURONALES: UNA APLICACIÓN A LA INFLACIÓN COLOMBIANA

FORECASTING TIME SERIES WITH NEURAL NETWORKS: AN APPLICATION TO THE COLOMBIAN INFLATION

Keywords:

Perceptron multicapas, modelos SARIMA, suavizamiento exponencial, combinación de pronósticos, componentes no observables (es)
Multilayer perceptron, SARIMA models, Exponencial smoothing, Combination of forecasts, Unobservable components (en)

Downloads

Authors

  • Juan Camilo Santana Universidade Federal de Pernambuc
Evaluar la capacidad de las redes neuronales en la predicción de series temporales es de sumo interés. Una aplicación que pronostique valores futuros de la serie de inflación colombiana permite mostrar que las redes neuronales pueden ser más precisas que las metodologías SARIMA de Box-Jenkins y el suavizamiento exponencial. Además, los resultados revelan que la combinación de pronósticos que hacen uso de las redes neuronales tiende a mejorar la capacidad de predicción.
Evaluating the usefulness of neural network methods in predicting the Colombian Inflation is the main goal of this paper. The results show that neural networks forecasts can be considerably more accurate than forecasts obtained using exponential smoothing and SARIMA methods. Experimental results also show that combinations of individual neural networks forecasts improves the forecasting accuracy.

Downloads

Download data is not yet available.

License

Copyright (c) 2006 Revista Colombiana de Estadística

Creative Commons License

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

  1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
  2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
  3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).