Resumen

COQUIS RIOJA, Itzel  y  CONTRERAS VALDEZ, Mario Iván. Causality Study on Financial Inclusion Issues with Data Science Techniques: The Mexican Case. The Anáhuac j. [online]. 2024, vol.24, n.1, pp.246-271.  Epub 26-Ago-2024. ISSN 2683-2690.  https://doi.org/10.36105/theanahuacjour.2024v24n1.09.

The current article explores the causes of financial inclusion among the Mexican population. It leverages data from the Encuesta Nacional de Inclusión Financiera (ENIF) (INEGI, 2021) to develop two machine learning models aimed at identifying individuals who are part of the financial system. These models are assessed using both artificial intelligence methodologies and traditional statistical significance tests. The findings suggest that factors such as education level, monthly income, future-oriented behavioral preferences over present ones, saving capacity, and access to smartphones are significant drivers that enhance the likelihood of financial inclusion. Consequently, there is a potential for implementing public policies to incentivize individuals to voluntarily adopt formal financial services.

Palabras llave : financial inclusion; artificial intelligence; machine learning.

        · resumen en Español     · texto en Inglés     · Inglés ( pdf )