NORMA eResearch @NCI Library

Machine Learning for Financial Inclusion and Safety: Empowering Women Against Violence

Fatobi, Adedoyin (2024) Machine Learning for Financial Inclusion and Safety: Empowering Women Against Violence. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration Manual]
Preview
PDF (Configuration Manual)
Download (1MB) | Preview

Abstract

This study examines how digital financial inclusion could help in reducing the genderbased inequalities that exists with access to financial technology. For the study, we explore the use of machine learning algorithms applied to dataset sources from the World Bank Demographic and Health Survey. The study utilized a number of machine learning models from the Random Forest classifier to Principal Component Analysis (PCA), and the Random Forest Regressor along with parametric tuning process using the RandomizedSearchCV to optimize the model parameters. Amongst other things, the study was able to show that the chosen models were appropriate for the designed tasks as model performance R squared values of 0.888 implying 88.8% accuracy, 0.9996 implying 99.9% accuracy. Extents of digital financial inclusion showed Sierra Leone, Russian Federation, Mongolia, El-Salvadore lacking behind in the post- Covid Era. Violence Hotspots against women were mainly concentrated in countries like Guinea, Mali, Sierra Leone, Ethiopia and Chad. The study further adapted the models to the data to create composite indices viz- the Financial Exclusion Index and the Vulnerability Index. The Financial Exclusion Index was used to plot geographical patterns and disparities in financial exclusion across countries telling the different areas of the extents of financial exclusion. The combination of the indices – Financial Exclusion Index and the Vulnerability Index also helped in distinguishing cluster variations for high, low and medium financial exclusion across the world.

Item Type: Thesis (Masters)
Supervisors:
Name
Email
Cosgrave, Noel
UNSPECIFIED
Onwuegbuche, Faithful
UNSPECIFIED
Subjects: H Social Sciences > HQ The family. Marriage. Woman > Domestic Violence
H Social Sciences > HG Finance > Fintech
T Technology > T Technology (General) > Information Technology > Fintech
H Social Sciences > HQ The family. Marriage. Woman > Gender
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in FinTech
Depositing User: Ciara O'Brien
Date Deposited: 02 Aug 2025 13:45
Last Modified: 02 Aug 2025 13:45
URI: https://norma.ncirl.ie/id/eprint/8418

Actions (login required)

View Item View Item