Employee Salary Satisfaction Analysis Using Machine Learning

In the fiercely competitive job market, where compensation plays a pivotal role in attracting and retaining talent, the accurate prediction of salaries is of paramount importance to both job seekers and employers. This research ad dresses the critical challenge of salary prediction by harnessing the capabilities of three robust regression models—AdaBoost Regressor, Gradient Boost Regressor, and Random Forest Regressor. It delves into the intricate fabric of salary determinants, including the company’s type of ownership, industry, geographical job location, requisite skills, and the level of seniority. Through rigorous evaluation utilizing various performance metrics such as R2-Score, Mean Square Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Performance Error (MAPE), the models’ efficacy is scrutinized. Notably, the results are compelling, with AdaBoost Regressor emerging as the undisputed frontrunner, boasting a remarkable R2-Score of 0.9998, MSE of 0.0004, and RMSE of 0.064. This research not only advances the state of the art in salary prediction but also equips employers with a powerful tool to make well-informed decisions about salary adjustments and employee compensation in the dynamic and competitive landscape of the job market.