Forecasting employees' promotion based on the personal indicators by using a machine learning algorithm

Abstract

Job promotion is considered one of the most important issues of importance in any organization, as it is vital for administrative development, and a means of motivating the worker for self-development and willingness to bear the burden and responsibility of work and the position attached to it, and thus it contributes to providing the necessary needs of the forces of mankind to occupy positions higher on the career ladder. Thus, this study aims to set up a sufficient framework to predict the promotion of an employee in an organization based on a variety of characteristics such as, but not limited to, the number of training, previous year rating, duration of service, awards earned, and average training score. Hence, this framework can be used and generalized to all prediction problems, not just our problem of predicting employee promotion. In this study, we used promotion data provided by Analytics Vidhya Data to test and prove the success of the framework. Our methodology is mainly composed of five phases: Input data, Data Pre processing, Data Manipulation, Data Modeling, and finally Data Evaluation. We constructed a new number of features in this study. Then we used several features including creating features and providing insights into the promotion and commitment of employees and using supervised learning techniques, namely XGBoost, Random Forest, Decision Tree, Logistic Regression, AdaBoost, and Gradient Boosting. Experimental results show that the XGBoost model has a higher accuracy of 94%, proving to be the most efficient. The result is accentuated by the high validation score similar to accuracy and efficiency. It is a very important and valuable study as it is the first study to predict employee promotion using the XGBoost classifier method.