Combination forecasts of tourism demand with machine learning models

Oscar Claveria, Enric Monte and Salvador Torra

Applied Economics Letters, 2016, vol. 23, issue 6, 428-431

Abstract: The main objective of this study is to analyse whether the combination of regional predictions generated with machine learning (ML) models leads to improved forecast accuracy. With this aim, we construct one set of forecasts by estimating models on the aggregate series, another set by using the same models to forecast the individual series prior to aggregation, and then we compare the accuracy of both approaches. We use three ML techniques: support vector regression, Gaussian process regression and neural network models. We use an autoregressive moving average model as a benchmark. We find that ML methods improve their forecasting performance with respect to the benchmark as forecast horizons increase, suggesting the suitability of these techniques for mid- and long-term forecasting. In spite of the fact that the disaggregated approach yields more accurate predictions, the improvement over the benchmark occurs for shorter forecast horizons with the direct approach.

Date: 2016
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (16)

Downloads: (external link)
http://hdl.handle.net/10.1080/13504851.2015.1078441 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:apeclt:v:23:y:2016:i:6:p:428-431

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/RAEL20

DOI: 10.1080/13504851.2015.1078441

Access Statistics for this article

Applied Economics Letters is currently edited by Anita Phillips

More articles in Applied Economics Letters from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().