Enhancing Efficiency of Employee Attrition Prediction Using Machine Learning and Ensemble Techniques

Anil, Linu (2024) Enhancing Efficiency of Employee Attrition Prediction Using Machine Learning and Ensemble Techniques. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (5MB) | Preview

Abstract

Employee turnover remains a major concern in organizations because it results in the cost of hiring new employees, loss of knowledge and interruption of organizational activities. This paper examines the applicability of machine learning to estimate the probability of employees’ turnover and help HR departments develop practical retention strategies. To prepare the dataset for modelling, initial data cleaning included outlier removal, employee data balancing, feature scaled using standard scalar on the IBM HR Employee dataset and hyper parameter tuning applied to the model optimization. In the modelling phase the Random Forest, XGBoost, and the stacking ensemble model were considered and experimented with. The stacking model, which uses tuned XGBoost and Random Forest as base models and Logistic Regression as the final estimator, was found most effective with an accuracy of 99.59 %, 100 % Precision, 98.30% Recall, and F1 score of 99.14%. The study also reveals how ensemble learning is beneficial for processing multiple dimensional HR data, managing problems such as class imbalanced data and noisy inputs. Although the data set restricts generality, the outcomes still prove the capability of machine learning for enhancing workforce analysis. This research is important to show how proactive measures such as predictive analytics can achieve strategic human resource management and organizational resilience.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Trinh, Anh Duong UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HD Industries. Land use. Labor > HD28 Management. Industrial Management > Human Resource Management Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning H Social Sciences > HD Industries. Land use. Labor > Issues of Labour and Work > Staff Turnover
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	01 Sep 2025 14:04
Last Modified:	01 Sep 2025 14:04
URI:	https://norma.ncirl.ie/id/eprint/8672

Actions (login required)

View Item