Tools
Tools
Ogunbowale, Oluwaseun Ayokunbi (2023) Explaining Neural Networks and Random Forest for Employee Retention. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration manual)
Download (1MB) | Preview |
Abstract
Employees are the foundation of every business or organization, and for any company or organization to succeed or flourish in business, the employer should cherish and respect its most important resource or workforce, which is staff, so there is a need to study employee retention. Employees have a propensity to quit an organization when treated in a bad way by the management team, which can also have a negative impact on the productivity of the business and lead to dissatisfaction and customer migration. The goal of this research is to identify the motivating factors that influence employee retention using Neural networks and Random Forests with Explainable AI.
This research made use of two machine learning techniques to solve the classification problem and explored factors that contributed to employee retention using two human resources (HR)datasets from Kaggle. The result was evaluated with the use of evaluation metrics and Explainable Ai tools, with an accuracy of 99 % in the Random Forest and 96% in Neural Networks in data. Two Explainable AI models such as LIME, which is a local interpretable Model-Agnostic explainer, and SHAP, which means Shapley Additive explainer was used. ‘Satifaction_level’, ‘number_project’,’average_montlyhour’, and ‘time_spend’ contributed positively to employee attrition with features positive and negative interactions that impacted the models.
Actions (login required)
 |
View Item |