Mapping Regional Characteristics of National Resilience Through Data Mining Approaches

Purposes This study aims to assess Indonesia's national resilience in the VUCA (Volatility, Uncertainty, Complexity, Ambiguity) era by evaluating regional resilience characteristics and their interrelationships. It focuses on the use of computational methods, including artificial intelligence, to classify regions based on national security conditions and identify effective measures to enhance national resilience. Study design/methodology/approach The research utilizes public policy simulations and a national resilience index assessment developed by Lemhannas. This system evaluates national resilience through regional assessments encompassing natural and social determinants. To analyze and classify regional resilience, computational methods such as K-means clustering and the Davies-Bouldin index test were employed. The study also highlights the interactions between variables and the importance of recognizing regional characteristics for policy formulation. Findings The study identified seven regional clusters that effectively enhance national resilience through K-means clustering and the Davies-Bouldin index test. These clusters provide precise data on regional similarities, which are crucial for developing targeted measures to bolster national resilience. The findings underscore the importance of computational methods in interpreting abundant data and formulating policies to improve regional and national resilience. Originality/value This research offers a novel approach to assessing and enhancing national resilience in Indonesia using artificial intelligence and computational methods. By identifying regional clusters and their characteristics, the study provides valuable insights for policymakers to develop effective strategies for strengthening national resilience. The integration of natural and social determinants in the assessment further enriches the understanding of regional and national resilience dynamics.