The Informal Economy as a Risk and an Opportunity for Sustainable Development - A Machine Learning-Based Approach

Aug 6, 2026

Upload by Maeve

Informality affects modern economies and societies and shapes progress toward the Sustainable Development Goals (SDGs). This study develops a data-driven analysis by integrating informal indicators into SDG predictive models. Machine learning methods, including Random Forest and XGBoost, are combined with feature selection using Chi-squared and Mutual Information. Findings reveal the complexity of the informality–sustainability link, with CO₂ emissions, agricultural income, and workplace safety as key determinants. Adding informal indicators improves estimation accuracy, supporting future sustainable development policy design.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages19

Reading Time48 min

AccessFree to download

Introduction

Literature review

Data and methods

Empirical results

Conclusions

THE INFORMAL ECONOMY ASA RISK AND AN OPPORTUNITY FOR SUSTAINABLE DEVELOPMENT: A MACHINE LEARNING-BASED APPROACH Roberto Dell'Anno1, Eduard Mihai Manta2􀀍, Tamara Maria Nae3 and Cristina Maria Geambasu4 1) University of Salerno, Italy 2)4)Bucharest University of Economic Studies, Romania 3)Bucharest University of Economic Studies, Romania and Ministry of Finance, Romania | Please cite this article as:
Dell'Anno, R., Manta, E.M., Nae, T.M. and Geambasu, C.M., 2025. The Informal Economy as a Risk and an Opportunity for Sustainable Development: A Machine Learning-Based Approach. Amfiteatru Economic, 27(Special Issue No. 19), pp. 1385-1403.
DOI: [https://doi.org/10.24818/EA/2025/S19/1385](https://doi.org/10.24818/EA/2025/S19/1385) | Article History
Received: 20 August 2025
Revised: 20 September 2025
Accepted: 18 October 2025 | | --- | --- | Abstract Informality has a considerable impact on modern economies and societies, including by influencing progress toward the Sustainable Development Goals (SDGs). In this research, we developed an innovative analysis of these relationships by integrating informal indicators into SDG predictive models. To achieve this, we employed machine learning methods – such as Random Forest and XGBoost – and feature selection techniques (Chi-squared and Mutual Information), thereby introducing a novel element to studies on the informal economy. The results highlighted the complexity of the relationship between informality and sustainability, showing that CO₂ emissions, agricultural income, and workplace safety emerged as key determinants. Moreover, the inclusion of informal indicators in the analysis enhanced the accuracy of the estimations. Thus, the methodological contributions of this study provided a robust and replicable framework useful for informing future public policies aimed at sustainable development. Keywords: informality, sustainable development, machine learning, Random Forest, XGBoost JEL Classification: O17, Q01, C55, J46, H26 􀀍 Corresponding author, Eduard Mihai Manta – e-mail: [eduard.manta@csie.ase.ro](eduard.manta@csie.ase.ro) This is an Open Access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. © 2025 The Author(s). Vol. 27 • Special Issue No. 19 • November 2025 1385 Introduction The informal economy represents a persistent and complex challenge in achieving the Sustainable Development Goals (SDGs) . It encompasses undeclared economic activities that occur outside the regulatory framework or are insufficiently captured in official statistics. From undeclared work and “envelope wages” to large-scale underground economies, these forms of informal activity are often left outside the scope of public policy, even though they play a significant role in shaping fiscal revenues, employment, and social equity at both the local and national levels. In this context, the present research aims to contribute to understanding the interaction between informal activities and sustainability. The economic relevance of this study lies in the fact that reducing the size of this sector can help diminish the budget deficit in most European countries by increasing fiscal revenues and strengthening public resources. At the same time, the objectives of the 2030 Agenda – such as eradicating poverty (SDG 1) and reducing inequalities (SDG 10) – are deeply interconnected with the phenomenon of informality, acting both as causal factors and as outcomes of informality. To develop more effective public policy options, this paper proposes an analysis of the impact of informal economic activities on sustainability through the application of a set of machine learning algorithms. This approach allows for the examination of relationships between sustainable development indicators and various forms of informality. By ap

FAQs

How does the study connect informality with Sustainable Development Goals (SDGs)?

It integrates informal indicators into SDG predictive models to analyze how different forms of informality relate to sustainability outcomes.

Which machine learning techniques and feature selection methods are used?

The research applies Random Forest and XGBoost, together with feature selection via Chi-squared and Mutual Information.

What variables were identified as key determinants of the informality–sustainability relationship?

CO₂ emissions, agricultural income, and workplace safety emerge as key determinants in the results.

Aug 6, 2026

Upload by Maeve