Use this URL to cite or link to this record in EThOS: https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.407455
Title: Intelligent systems for modelling economic policies
Author: Makriyannis, Elpida
ISNI:       0000 0001 3617 2507
Awarding Body: University of London
Current Institution: University College London (University of London)
Date of Award: 2004
Availability of Full Text:
Access from EThOS:
Full text unavailable from EThOS. Please try the link below.
Access from Institution:
Abstract:
This thesis introduces 'intelligent country modelling', an intelligent decision-making tool to analyse macroeconomic structural issues. The Chinese dual-track economic model is selected to investigate the transitions from a centrally planned to a market-oriented economy and from a rural-agricultural to an urban-industrialised country. The model analyses Chinese provinces according to their growth type determining the regions that should adopt more rapid or gradualist policies. It also explores China's trading partner's over- or under-traded behaviour relative to bilateral trade flow knowledge. The understanding accomplished by this intelligent tool provides insight into China's future economic prospective thus assisting policy makers to design alternative strategies for country-specific sustainable equally distributed growth. The thesis presents the design, implementation and evaluation of a new intelligent systems model, the Growth and Trade Country Analyser (GTCA), to combine the analysis of China's interior growth structure and international trade actions. The technical implications when considering building such a system are significant. Firstly, complex multivariate provincial data and regional growth indicators that occupy insignificant values or different provincial growth descriptions leave the assessed database sparse and incomplete. Secondly, asymmetric bilateral trade flows caused from different magnitude data sets for developed and developing countries make crucial prediction points noisy. These implications are solved by employing the GTCA that applies effective non-trivial detection and translation of explicit knowledge structures where complexity makes it impossible for human observation, statistical analysis or other intelligent methods. The GTCA integrates two separate stages. The first stage employs Self-Organising Maps (SOMs) which combine clustering and projection algorithms to analyse the complex joint effect of the long-term growth factors and the critical properties of provincial growth structure by visualising and locating individual Chinese provinces on the map according to their growth type at a 2D level. The second stage uses genetic programming to determine the symbolic relationship that predicts over- or under-traded partner behaviour in China's real-world trading environment from interacting sets of bilateral trade flows. Intelligent country modelling contributes to the detection, extraction and translation of previously unknown potentially useful economic growth and trade data element relationships. It reformulates policy goals through a feedback loop based on the results solving technical implications including noisy asymmetric trade flows and multivariate provincial growth range data. This model tests the SOM's ability to characterise complex provincial growth indicators and visualise important features of different dimensionality. This intelligent decision-making tool is believed to be the first designed to analyse economic policies and also the first intelligent model developed to identify China's economic growth structure and trading environment through observation of its reform period.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.407455  DOI: Not available
Share: