Automatic identification of ARIMA models with neural network

Authors

  • Balázs Lénárt
https://doi.org/10.3311/pp.tr.2011-1.07

Abstract

The paper investigates an artificial intelligence based demand forecasting method. A neural network driven automatic ARIMA model identification is being introduced. The limitations of the current methods are shown and a new identification concept is presented. It is being discussed that the model identification with a neural network is less sensitive to input errors through its intuitive capability, additionally after a certain number of training steps the algorithm is able to identify time series with unknown characteristics.

Keywords:

Neural Network; ARIMA; identification

How to Cite

Lénárt, B. (2011) “Automatic identification of ARIMA models with neural network”, Periodica Polytechnica Transportation Engineering, 39(1), pp. 39–42. https://doi.org/10.3311/pp.tr.2011-1.07

Issue

Section

Articles