Assessing regional competitiveness, an approach using nonlinear machine learning models

What is it about?

This study uses artificial intelligence (machine learning) to measure the competitiveness of Peru's regions more accurately than traditional methods. It analyzes data from 25 regions (between 2016 and 2023) in areas such as the economy, education, and transportation, finding hidden patterns that help understand why some areas develop more than others. The results are so accurate that they can guide governments to better invest their resources, for example, deciding whether to build a road or improve schools in a specific area. This not only helps reduce inequalities but also serves as a model for other countries.

Featured Image

Photo by 高德 達人 on Unsplash

Photo by 高德 達人 on Unsplash

Why is it important?

This study stands out for its innovative approach, applying advanced nonlinear machine learning (ML) models—such as gradient boosting, random forest, and neural networks—to measure regional competitiveness in Peru, a challenge traditionally addressed with rigid statistical methods that fail to capture the true complexity of the data. Unlike previous research, this study uses the ODD protocol to ensure transparency and replicability, while analyzing 25 Peruvian regions (2016–2023) under five key pillars: economy, government, infrastructure, businesses, and population. The results are compelling: the ML models achieve an R² of 0.97, far outperforming conventional techniques, and reveal critical variables that distort the Regional Competitiveness Index (IRCI). This breakthrough is unique because it not only solves an academic problem—the nonlinear measurement of competitiveness—but also offers governments and businesses an actionable framework: for example, identifying whether investing in roads or education will have a greater impact on development in a specific region. To broaden its reach, the study should emphasize three key elements: (1) its applicability in developing countries (Peru as a paradigmatic case of regional inequalities), (2) the potential to reduce biases in public policy (using ML to prioritize limited resources), and (3) its methodological advantage (open protocols that other researchers can replicate in their contexts). To attract more readers, the title and abstract should include terms such as "AI for economic development," "predictive competitiveness," or "data-driven decisions in Latin America," appealing not only to academics but also to policymakers, consultants, and NGOs. A clear call to action—"How to optimize public resources with artificial intelligence? This study proves it's possible"—can generate engagement on social media and specialized media, positioning the work as a tool rather than a theoretical analysis. The combination of scientific rigor, practical applications, and accessible language is key to multiplying its impact.

Perspectives