Evolving hybrid neural networks with swarm intelligence for forecasting ASEAN inflation

Date of Publication

2018

Document Type

Master's Thesis

Degree Name

Master of Science in Economics

College

School of Economics

Department/Unit

Economics

Thesis Adviser

Dickson A. Lim

Defense Panel Member

Brian C. Gozun

Abstract/Summary

Macroeconomic policy depends greatly on forecasting. Artificial neural networks (ANNs) such as multilayer perceptron's (MLPs) and recurrent neural networks (RNNs) can learn the nonlinearities of time series, making them strong candidates for improving economic forecasting. We forecast inflation rates from the ASEAN region using the standard automatic SARIMA as benchmark, the MLP, a state of the art RNN called Long Short Term Memory (LSTM), and a novel hybrid SARIMA-ANN model. Neural networks, however, are difficult to design and train. Thus, we let the network hyper parameters evolve using a recent Swarm Intelligence optimization algorithm: Grey Wolf Optimization (2014). We compare the one step and 12-steps ahead forecast accuracy of the evolving ANNs with SARIMA. Results show a clear superiority of the evolving SARIMA-ANN over every other model, with the evolving MLP at second, SARIMA at third, and LSTM performing the worst.

Abstract Format

html

Language

English

Format

Electronic

Accession Number

CDTG007598

Shelf Location

Archives, The Learning Commons, 12F Henry Sy Sr. Hall

Physical Description

1 computer disc ; 4 3/4 in.

Keywords

Neural networks (Computer science); Economic forecasting; Business forecasting

This document is currently not available here.

Share

COinS