Integrating Data Mining and Decision Support Systems for Optimizing New Employee Selection

Abstract

The employee recruitment process is a critical component of human resource management that requires accurate and data-driven decision-making. Traditional selection methods often rely on subjective assessments, leading to inconsistencies and inefficiencies. This study proposes an integrated approach combining data mining techniques with a decision support system (DSS) to assist in selecting the most suitable job applicants. Using classification algorithms such as Decision Tree and Naive Bayes, historical recruitment data including educational background, work experience, psychological test scores, and interview evaluations are analyzed to extract meaningful patterns. These insights are incorporated into a web-based DSS interface that provides structured recommendations to HR personnel. The proposed system was evaluated using accuracy metrics and user feedback, demonstrating an improvement of up to 85% in decision accuracy compared to manual evaluation methods. This integration not only optimizes candidate selection but also reduces bias and time consumption in the recruitment process. The research contributes to the advancement of intelligent decision-making in human capital management by utilizing predictive analytics and automated evaluation support. The model is adaptable and can be customized across various organizational contexts, offering practical implications for digital transformation in HR operations.