<![CDATA[ABSTRACT. Lecturer performance appraisal is a process in evaluating lecturer performance and lecturer work output. This research was conducted to classify the performance of lecturers by utilizing data mining techniques. This study aims to facilitate the provision of information and evaluation to lecturers and as a decision-making material. The research method used is the Knowledge Discovery in Database (KDD) method, which consists of the following stages: Data Selection, Preprocessing/Cleaning, Data Transformation, Data mining, and Enterpretation/Evaluation. The application of the method used in this study is the K-Means Clustering algorithm. The steps taken in analyzing and classifying performance start with several centroid values from a random center point. The K-Means algorithm process ends if there is no change in the centroid value between one iteration and another. The test was carried out using the RapidMiner Studio 9.10 application and using the Davies-Bouldin Index (DBI) evaluation with 983 data input data, so that the results of the lecturer performance assessment were based on student satisfaction, namely very good cluster 312 (31.74%) student data, good cluster 401 (40.79%) student data, cluster data is quite good 189 (19.23%) student data, and cluster data is not good 81 (8.24%) student data. And the DBI result is 0.270 or 27%, so the accuracy of the cluster results is good, because the DBI value is close to zero. Keywords: Lecturer performance assessment, KDD, Data mining Clustering, K-Means, DBI]]>
