<![CDATA[Determining salary increases is a crucial policy in human resource management that directly influences employee retention and organizational stability. However, this process is frequently marred by managerial bias and a lack of transparency. This study develops a Decision Support System (DSS) specifically targeted at providing a justifiable framework for salary adjustments based on objective workload metrics. By employing the Analytic Hierarchy Process (AHP), the system decomposes the decision problem into a structured hierarchy, prioritizing "Hours per Week" as the primary workload indicator. The model was validated using a comprehensive salary prediction dataset. Results indicate that the Workload criterion achieved the highest weight (0.648), significantly outweighing Education (0.229) and Experience/Age (0.122). Comparative analysis with a Random Forest classification model (87.3% accuracy) demonstrates that while machine learning excels in predictive performance, the AHPbased DSS provides the essential transparency required for ethical HR interventions. This system targets the reduction of perceived unfairness, thereby fostering a more meritocratic organizational culture.]]>
Copyrights © 2026
