Convergence and Divergence in Asian Countries Through Machine Learning Algorithms

Abstract

Abstract

Objective of this paper is to empirically examine the convergence of operating economies between five selected Asian countries (ie Thailand, Singapore, Malaysia, Philippines and Indonesia). In particular, it seeks to investigate how increased economic integration impacts levels of income between countries among the five founding members of ASEAN. The new Machine Learning (ML) approach was implemented alongside panel data analysis (GMM), and implementation of the KOF Globalization Index.

Results The Generalized Method of Moments (GMM) highlights that the theory of endogenous growth appears to be supported for selected Asian countries, which shows evidence of differing strengths due to unequal growth and polarization dynamics. Addressing the technical issues raised by the econometrics approach, the new ML algorithm provides contrasting but interesting results.

Using the KOF Globalization Index, the authors confirm how the last phase of globalization governed the conditions for economic convergence among sample members. Using the KOF Globalization Index, the authors confirm how the last phase of globalization set the conditions for economic convergence among sample members. In fact, the new LSTM algorithm has provided consistent evidence supporting the existence of convergent forces.

in fact, the results highlight the effectiveness of our chosen experiment and algorithm. High predictability of the author's model and no self-alignment in values ​​shows convergence between economies.