Analyzing Income Inequalities across Italian regions - Instrumental Variable Panel Data, K-Means Clustering and Machine Learning Algorithms

Aug 3, 2026

This study examines income inequality across Italian regions by integrating instrumental variable panel data models, k-means clustering, and machine learning algorithms. Econometric techniques address endogeneity and support causal identification behind regional disparities. K-means clustering, optimized with the elbow method, groups regions according to inequality patterns, while predictive models (random forest, support vector machines, and decision tree regression) estimate inequality trends and key determinants. Results confirm a persistent North-South divide and highlight the most disadvantaged regions: Campania, Calabria, and Sicily.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages47

Reading Time1 h 58 min

AccessFree to download

Introduction

Methodological approach

Literature context

Data-driven prediction and clustering (planned)

Main findings and policy implications

Munich Personal RePEc Archive Analyzing Income Inequalities across Italian regions: Instrumental Variable Panel Data, K-Means Clustering and Machine Learning Algorithms Antonicelli, Margareth and Drago, Carlo and Costantiello, Alberto and Leogrande, Angelo IULM University, Unicusano University, LUM University Giuseppe Degennaro, LUM University Giuseppe Degennaro 5 May 2025 Online at [https://mpra. ub. uni-muenchen. de/124910/](https://mpra. ub. uni-muenchen. de/124910/) [MPRA Paper No. 124910](MPRA Paper No. 124910) , [posted 01 Jun 2025 11:26 UTC](posted 01 Jun 2025 11:26 UTC) Analyzing Income Inequalities across Italian regions: Instrumental Variable Panel Data, K-Means Clustering and Machine Learning Algorithms Margareth Antonicelli IULM University, Milan [margaret.antonicelli@iulm.it](margaret.antonicelli@iulm.it) Carlo Drago Unicusano University, Rome [carlo.drago@unicusano.it](carlo.drago@unicusano.it) Alberto Costantiello LUM University Giuseppe Degennaro, Casamassima [costantiello@lum.it](costantiello@lum.it) Angelo Leogrande LUM University Giuseppe Degennaro, Casamassima [leogrande.cultore@lum.it](leogrande.cultore@lum.it) Abstract This study examines income inequality across Italian regions by integrating instrumental variable panel data models, k-means clustering, and machine learning algorithms. Using econometric techniques, we address endogeneity and identify causal relationships influencing regional disparities. K-means clustering, optimized with the elbow method, classifies Italian regions based on income inequality patterns, while machine-learning models, including random forest, support vector machines, and decision tree regression, predict inequality trends and key determinants. Informal employment, temporary employment, and overeducation also play a major role in influencing inequality. Clustering results confirm a permanent North-South economic divide and the most disadvantaged regions are Campania, Calabria, and Sicily. Among the machine learning models, the highest income disparities prediction accuracy comes with the use of Random Forest Regression. The findings emphasize the necessity of education-focused and digitally based policies and reforms of the labor market in an effort to enhance economic convergence. The study portrays the use of a combination of econometric and machine learning methods in the analysis of regional disparities and proposes a solid framework of policy-making with the intention of curbing economic disparities in Italy. Keywords: Income Inequality, Regional Disparities, Machine Learning, Labor Market, Digital Divide. JEL Codes: C23, C38, C45, O15, R11, R58 . 1. Introduction One of the most salient issues of economic analysis and public policy is the analysis of income disparities because income disparities influence social welfare, political stability, and economic development directly. Italy has a stunning example of economic disparities at the regional level with a lasting cleavage between the South and the North of the country. This economic cleavage has a long-lasting and structural character and it emerges through large disparities at the income and employment rates and investment in the infrastructure and development perspectives. The persistence of the disparities raises the crucial issue of the efficiency of economic policies in inducing the convergence of the different regions and the attainment of a lasting and sustainable economic development. An original methodological approach that combines cutting-edge econometric models and machine learning techniques can be applied in the analysis of economic disparities among the territories of Italy. The use of instrumental variable panel data models allows scholars to confront the issue of the problem of causality in the analysis of econometric models and the elimination of omitted variables' and endogeneity-induced biases. The employment of unsupervised methods of clustering, su

FAQs

How does the study handle causality when estimating income inequality?

It uses instrumental variable panel data models to address endogeneity and reduce biases caused by omitted variables.

What role does K-means clustering play in the analysis?

K-means clustering, tuned with the elbow method, classifies Italian regions into groups with similar income inequality patterns.

Which machine learning model achieves the highest prediction accuracy?

Random Forest Regression provides the highest accuracy for predicting income disparities in the study.

Aug 3, 2026

Uploaded by River Wang