Translator Disclaimer
15 March 2019 Use of Artificial Neural Networks and ARIMA to Forecasting Consumption Sawnwood of Pinus sp. in Brazil
Author Affiliations +
Abstract

The objective of this study was to analyze the application of an artificial neural networks model and an ARIMA model to predict the consumption of sawnwood of pine. For this, we use real and secondary data collected and obtained from a historical data source, corresponding to the period from 1997 to 2016, which were later tested to generate the forecast models. Based on economic and statistical criteria, six explanatory variables were used to fit the best model. The choice of the model was made based on Mean Squared Error, Mean Absolute Error, Theil U metric, Percentage Error of Forecast and Akaike value information criterion. The results indicated that the models generated through the ARIMA model presented better performance when compared to the artificial neural network. The best adjusted model estimated a reduction of 1.33% in consumption of sawnwood of pine in Brazil for the period between 2017 and 2020.

D.A. Buratto, R. Timofeiczyk Junior, J.C.G.L. Silva, J.R. Frega, M.S.S.A. Wiecheteck, and C.A. Silva "Use of Artificial Neural Networks and ARIMA to Forecasting Consumption Sawnwood of Pinus sp. in Brazil," International Forestry Review 21(1), 51-61, (15 March 2019). https://doi.org/10.1505/146554819825863735
Published: 15 March 2019
JOURNAL ARTICLE
11 PAGES


SHARE
ARTICLE IMPACT
RIGHTS & PERMISSIONS
Get copyright permission
Back to Top