<![CDATA[This research is important because public interest in the KIP Kuliah Scholarship continues to increase. However, many educational institutions still use manual selection which is prone to bias and less effective in data management. Therefore, a method is required to make the selection process more efficient; the K-Means and K-Nearest Neighbor methods are two data processing methods that have been proven effective in various applications, including in the field of data processing. In this study, the K-Means and K-Nearest Neighbor methods are used to select scholarship recipients to increase efficiency in the process. Based on the processing carried out, there were 1257 participants who were then grouped into three clusters: Cluster 0 with 739 data points, Cluster 1 with 290 data points, and Cluster 2 with 228 data points. Testing using the K-Nearest Neighbor algorithm was carried out by evaluating the appropriate k values, specifically 27, 31, 35, 41, 45, and expanded to 185 to obtain the optimal value, namely K-155 and produced as many as 155 people who were deemed worthy and qualified according to the specified criteria. The combination of K-Means and K-NN algorithms resulted in an accuracy of 89.72% accomplished in 16 seconds. This combo can recognize data with excellent accuracy in a fast time while minimizing errors. The test results suggest that this technique is effective in selecting applicants based on the criteria and quotas established, thus it can be used as a guideline for future selection.]]>
Copyrights © 2025
