USP Electronic Research Repository

Modeling emigration of Fiji's population using Artificial Neural Network

Qiokata, Viliame and Khan, Mohammad G.M. (2015) Modeling emigration of Fiji's population using Artificial Neural Network. [Conference Proceedings]

Full text not available from this repository.

Abstract

Because emigration plays a major role in the national demographic structure, it is vital that some model be identified to forecast population by identifying prevailing emigration trends, apart from other contributing factors. The choice of which model to use depends on which ones incur minimal errors in the forecasting process. This paper proposes an Artificial Neural Network (ANN) model for forecasting emigration for Fiji population components during the years from 1986 to 2012. The proposed ANN model is also computed with the Naive Method as the benchmark method for modeling emigration of Fiji's population. The performances of the two models used are based on the values of the various error functions used such as the Root Square Mean Error (RSME), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE).

Item Type: Conference Proceedings
Subjects: H Social Sciences > H Social Sciences (General)
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: College of Foundation Studies
Faculty of Science, Technology and Environment (FSTE) > School of Computing, Information and Mathematical Sciences
Depositing User: Fulori Nainoca
Date Deposited: 18 Jul 2016 09:22
Last Modified: 15 Mar 2017 15:50
URI: http://repository.usp.ac.fj/id/eprint/9065
UNSPECIFIED

Actions (login required)

View Item