Predicting Employee Promotions: Investigating the influence of Training, KPI Achievement, And Training Score

Abstract

When thinking about human resources, one of the most crucial procedures is the promotion process. Managers may inspire their staff and ensure the company's longevity with a well-structured promotion procedure. For many workers, the prospect of a promotion serves as a significant extrinsic motivator. Maintaining the employee's present level of involvement and dedication to the company is a win-win. For the company, it's a key tool for both rewarding employees and keeping tabs on their performance. Promotion candidates are evaluated based on a wide range of criteria, including but not limited to: age, training score, organisational commitment, seniority, performance level, skills, and awards. The purpose of this research is to examine a prediction approach that takes into account the factors used by Machine Learning algorithms like Random Forest, Support Vector Machine, and Artificial Neural Network to assess candidates for promotions. By using the ROS technique, Random Forest attained the best performance, boasting 98% accuracy, 96% precision, 1.0% recall, and 98% f1- score values. Human resources and managers might utilise this research to forecast promotion chances, allowing them to set appropriate criteria for employees.