Analyzing Gender Disparities in Corporate Leadership Using Machine Learning Techniques on Global Board Member Data

Moorthy, Geerthana (2025) Analyzing Gender Disparities in Corporate Leadership Using Machine Learning Techniques on Global Board Member Data. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (817kB) | Preview
Preview	PDF (Configuration Manual) Download (532kB) | Preview

Abstract

Gender disparity in corporate leadership remains a significant and persistent issue in the global business landscape. This research addresses the challenge of analyzing the factors contributing to this disparity by developing a comprehensive methodological framework. Due to the scarcity of granular, publicly available data on corporate board members, this study pioneers an approach based on a large-scale synthetic dataset comprising 200,000 records for 20,000 companies. This dataset is engineered to reflect realistic global distributions and inherent biases related to industry, region, and company size. A machine learning pipeline is then constructed to predict the gender of a board member using a profile of individual and corporate attributes. The pipeline requires significant feature engineering, pre-processing and dimensionality reduction through Principal Component Analysis (PCA). Several classification models were developed, and a tuned XGBoost model emerged as the final model in the pipeline. The final model reports a test accuracy of 79.14% and an AUC of 0.7751. The evaluative process identifies a large performance disparity between the classes, specifically a low recall of 26.11% in the female category, indicating how the model was biased as a result of learning from imbalanced training data. The primary contribution of this study is to provide a replicable model to examine and study demographic disparities using synthetic data and machine learning, but also presents evidence of how algorithms can internalize and manifest existing systemic biases present in training data.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Anant, Aaloka UNSPECIFIED
Subjects:	H Social Sciences > HQ The family. Marriage. Woman > Gender H Social Sciences > HD Industries. Land use. Labor > Large Industry. Corporations. H Social Sciences > HM Sociology > Leadership H Social Sciences > HD Industries. Land use. Labor > HD28 Management. Industrial Management > Human Resource Management > Leadership 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:	26 Aug 2026 09:04
Last Modified:	26 Aug 2026 09:04
URI:	https://norma.ncirl.ie/id/eprint/9646

Actions (login required)

View Item