What is it about?

This study aims to analyze the effects of data pre-processing on the forecasting performance of neural network models. We use three different Artificial Neural Networks techniques to predict tourist demand: multi-layer perceptron, radial basis function and Elman neural networks. The structure of the networks is based on a multiple-output approach. We use official statistical data of inbound international tourism demand to Catalonia (Spain). We compare the forecasting accuracy of four processing methods for the input vector of the networks: levels, growth rates, seasonally adjusted levels and seasonally adjusted growth rates.

Featured Image

Why is it important?

When comparing the forecasting accuracy of the different inputs for each visitor market and for different forecasting horizons: - We obtain significantly better forecasts with levels than with growth rates. - We also find that the use of seasonally adjusted series significantly improves the forecasting performance of the networks. These results: - Show the convenience of deseasonalizing the time series when using neural networks with forecasting purposes. - Reveal that, when using seasonal data, neural networks performance can be significantly improved by working directly with seasonally adjusted levels.


Neural networks are increasingly used with forecasting purposes in many fields. Yet there seems to be no consensus in which is the optimal way to introduce the inputs. This research sheds some light about the need for data pre-processing for neural network-based forecasting.

Oscar Claveria
AQR-IREA, Univeristy of Barcelona

Read the Original

This page is a summary of: DATA PRE-PROCESSING FOR NEURAL NETWORK-BASED FORECASTING: DOES IT REALLY MATTER?, Technological and Economic Development of Economy, November 2015, Vilnius Gediminas Technical University, DOI: 10.3846/20294913.2015.1070772.
You can read the full text:




The following have contributed to this page