Mining Model for Employees Performance Prediction

Managers and decision-makers in various industries now recognize the critical importance of Human Resource Management (HRM) in identifying highly qualified employees. This study explores the application of data mining techniques in predicting employee performance, leveraging HRM practices to effectively manage talent through comprehensive employee datasets and advanced algorithms. The primary goal is to develop a classification model using data mining techniques to provide managers and HR professionals with a data-driven tool for enhancing talent management and optimizing employee placement.
Previous studies often relied on intuition or anecdotal evidence rather than rigorous data mining techniques. This research addresses this gap by implementing a data-driven approach, achieving higher accuracy rates in predicting employee performance. The research question is tackled by constructing a classification model utilizing Decision Tree (DT), Naive Bayes, and Support Vector Machine (SVM), with the implementation carried out using Rapid Miner. The model incorporates demographic and work history factors to accurately predict employee performance.
The key impact of this research is the high accuracy rates of the classification model, ranging from 85.7% to 100%, depending on the algorithm used. By identifying critical factors influencing employee performance, the model enables managers to make informed, data-driven decisions. This leads to optimized employee placement, improved identification of high-potential individuals, and overall enhanced organizational effectiveness. Additionally, the model's predictive capabilities can reduce hiring risks and improve workforce productivity and engagement.