Validity of unbalanced growth theory and sectoral investment priorities in Indonesia: Application of feature ranking methods

Abstract

This study develops a new approach for testing the validity of unbalanced growth theory as well as determining the sectoral priorities for investment in Indonesia over the period 1995-2015. To this end, the high linkage sector(s) is identified through the input-output framework. Afterward, two different approaches, multiple linear regression and multi-layered perceptron (MLP) artificial neural network, are applied to capture the linear and nonlinear relationships between the extracted engine sectors and gross domestic product growth. Given that the detection of sector ranking is crucial for preparing a proper development plan, in the same vein we apply two types of feature-ranking methods (namely, stepwise regression and ant colony optimization (ACO-MLP based). The findings suggest a consistent relationship between the theory and economic growth in both linear and nonlinear models. However, the nonlinear model outperforms its competitor. In general, we find that the manufacturing sector is the most strategic sector in Indonesia, as it has been ranked first in both linear and nonlinear forms. Hence, its development path could be reinforced by more investment in this leading sector and then followed by investment in construction, hotels and restaurants, and agriculture.