<![CDATA[Ensuring a fair and well-targeted scholarship distribution process remains one of the major challenges faced by private universities. In many cases, scholarship recipient selection is carried out subjectively and lacks support from a systematic approach. This study proposes a hybrid method using K-Means Clustering and the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) to optimize the scholarship selection process. Student data covering academic aspects (GPA), socio-economic factors (parental income and occupation, family dependents), and non-academic components (achievements and organizational activity) were analyzed using the K-Means algorithm to group students with similar characteristics. Silhouette Score validation produced four optimal clusters with a score of 0.1683. Subsequently, the TOPSIS method was applied to rank the clusters based on predetermined criteria. The results show that Cluster 4 achieved the highest ranking with a score of 0.7853, followed by Cluster 3 (0.6359), Cluster 1 (0.6014), and Cluster 2 (0.5807). Attribute contribution analysis revealed that GPA is the dominant factor (48.61%–52.26%), followed by parental income (16.15%–19.59%) and family dependents (11.36%–12.09%). The developed model successfully provides an objective foundation for allocating scholarship quotas based on student group characteristics. This study contributes to the development of a more transparent and accountable scholarship selection system.]]>
