EconPapers    
Economics at your fingertips  
 

Exploring Neural Network Models in Understanding Bilateral Trade in APEC: A Review of History and Concepts

Francis Mark A. Author_Email: qfrancis@pids.gov.ph Quimba and Mark Anthony A. Barral

No DP 2018-33, Discussion Papers from Philippine Institute for Development Studies

Abstract: This paper seeks to understand certain frameworks that can be used to improve the analysis and prediction of trade flows within the Asia-Pacific Economic Cooperation economies using neural networks. Discussions include the history of neural network development, the biological neuron, the artificial neuron, and the potential use of neural networks in trade analysis. This paper also compares the different estimation procedures of the gravity model–-Ordinary Least Squares, Poisson Pseudo Maximum Likelihood, and Gamma Pseudo Maximum Likelihood-–with the neural network. Study finds that the neural network estimation of the gravity equation is superior over the other procedures in terms of explaining the variability of the dependent variable (export) around its mean and in terms of the accuracy of predictions.

Keywords: artificial intelligence; neural networks; machine learning; gravity model; Ordinary Least Squares; Poisson Pseudo Maximum Likelihood; Gamma Pseudo Maximum Likelihood; trade; Asia-Pacific Economic Cooperation (search for similar items in EconPapers)
Date: 2018
References: Add references at CitEc
Citations: Track citations by RSS feed

Downloads: (external link)
https://serp-p.pids.gov.ph/serp-p/download.php?d=6735&s=3 (application/pdf)

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:phd:dpaper:dp_2018-33

Access Statistics for this paper

More papers in Discussion Papers from Philippine Institute for Development Studies Contact information at EDIRC.
Bibliographic data for series maintained by Aniceto Orbeta ().

 
Page updated 2020-07-03
Handle: RePEc:phd:dpaper:dp_2018-33