Affiliations: School of Economics and Management, Jiaozuo University, Jiaozuo, China
Correspondence:
[*]
Corresponding author: Xiaoxiang Dong, School of Economics and Management, Jiaozuo University, Jiaozuo, China. E-mail: dong_xiaoxiang@outlook.com.
Abstract: Regional economic development objectives are improved economic, political, and social conditions in a certain area. Investment, production, innovation, wealth, and affluence are the four stages of regional economic development that may be identified in each selected area. It becomes more reliant on technological advancements in the industry and less on locally sourced production inputs as the economy region grows. The regional economic growth issue is inequality in the rates of improvement of subnational geographic regions and inequalities in the distribution of wealth. Intellectual algorithms or enhanced and hybrid algorithms based on machine learning, such as Fuzzy C-means clustering (FCM), principal component analysis, and algorithm, can newly achieve more appropriate solutions to practical issues of discrete, non-linear, non-differentiable, and various constraints. A hybrid algorithm combines two or more other algorithms that solve the same problem. Hence, this paper proposes a Principal Component Analysis for the Sustainable Regional Economic Development (PCA-SRED) model to enhance the efficiency in examining regional economic changes and industrial development zones. The data are taken from the Organization for Economic Cooperation and Development (OECD) regional statistics dataset. Using PCA, industries may be categorized based on shared criteria, and the whole spatial distribution law of datasets and common patterns can be uncovered. To create a long-lasting regional economic development plan, it is crucial to categorize, compare, and evaluate the economic growth level of several areas. The research outcomes illustrate that the hybrid algorithms have high accuracy and a fast convergence rate because they can replicate the smart behavior of some clusters in nature while examing the variances in regional economic growth. The experimental outcomes illustrate that the recommended PCA-SRED model enhances the accuracy ratio by 98.2%, industry production ratio by 95.6%, regional economic change prediction ratio by 96.4%, and economic efficiency ratio by 97.8% compared to other popular models.
Keywords: Regional economic development, sustainability, hybrid algorithms, principal component analysis
