Gender bias analysis in Machine Learning prediction for the secondary school exit exam in Colombia

Pinzon Velandia, Karen Samantha (2024) Gender bias analysis in Machine Learning prediction for the secondary school exit exam in Colombia. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

This research looks at the potential gender bias by analysing the performance prediction using machine learning models applied to the high school exit exam in Colombia focused on the Boyaca region. Using the exam data for the year 2022, the study compares the accuracy of Random Forest Classifier and Logistic Regression Tree for different gender-based experiments and concludes that there is no significant difference in the accuracy between training the models with female and male data, or training with only one of the genders. The significance was determined by a one-way ANOVA with a 0.05 tolerance. The average accuracy for both models was 66% showing no difference between the models applied. However, the models show a better accuracy when predicting the true negative values.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Milosavljevic, Vladimir UNSPECIFIED
Subjects:	L Education > LB Theory and practice of education > LB1603 Secondary Education. High schools Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science 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 Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	25 Aug 2025 10:00
Last Modified:	25 Aug 2025 10:00
URI:	https://norma.ncirl.ie/id/eprint/8612

Actions (login required)

View Item