<![CDATA[Lecturer performance is very important to support the progress of higher education. Determination of lecturer performance is based on Tri Dharma activities, including: teaching, research and community service. This study aims to build a model that can predict the predicate of lecturers from the activities carried out. The best model is obtained by comparing the use of two algorithms, namely Decision Tree and Naive Bayes. Data mining methods use the CRISP-DM method, namely business understanding, data understanding, data preparation, modeling, evaluation, and development. Performance testing of training data using K Fold Cross Validation. The modeling results with this performance show that the Decision Tree algorithm has better performance with 94.70%, accuracy, 93.24% precision and 96.33% recall, while Naïve Bayes algorithm has performance with 92.95%, accuracy 90.08% and 96.33%. This shows that modeling using the Decision Tree algorithm can be used as a model in determining lecturer performance.]]>
Copyrights © 2023
