Abstract

Proper and objective selection of high potential employees to promote them is a major dilemma in the Human Resources (HR) department, more so in sensitive and hierarchal environments in the public sector where subjectivity is likely to take place. This paper is based on this ubiquitous issue, and it seeks to develop, experiment, and examine a clear and equitable machine learning model that can forecast the possibility of an employee to get a promotion according to organized past HR records. The technique was solid preprocessing, alleviation of extreme class imbalances on the basis of the Synthetic Minority Over-sampling Technique (SMOTE), as well as comparative examination of intricate (XGBoost) and very clarifiable (Logistic Regression) classifiers. However, the XGBoost model has the highest predictive power (F1-Score: 0.4909), but the Optimized Logistic Regression model has an alternative F1-Score of 0.4639; this is why the latter is chosen in favor of the former because it is the most critical in terms of transparency and auditability in the public sector. The important features analysis revealed that organizational structure (departmental membership), the long term past performance, and tenure played a key role in promotion. Notably, a fairness test showed that there was predictive equity in terms of genders, which proved the ethical value of the model. The research presents a valid, objective and gender-neutral decision support framework, which offers a needed entry point via which establishments can pay more attention to meritocracy and confidence in their talent handling processes by individuals.

Library of Congress Subject Headings

Promotions--Forecasting--Data processing; Public administration--Data processing; Predictive analytics; Machine learning

Publication Date

12-2025

Document Type

Thesis

Student Type

Graduate

Degree Name

Professional Studies (MS)

Department, Program, or Center

Graduate Programs & Research

Advisor

Sanjay Modak

Advisor/Committee Member

Ayman Ibrahim

Campus

RIT Dubai

Plan Codes

PROFST-MS

Download

Share

COinS