LECTURERS ADMISSIONS SELECTIONS MODEL USING FUZZY K-NEAREST NEIGHBOR METHOD

Abstract

Higher Education, or tertiary education, is the final stage which is optional in formal education. It is usually organized in the form of a university, academy, seminary, high school, or institute. Every tertiary institution needs qualified and professional educators because they have an important role in the process of implementing the Tri Dharma of Higher Education. Recruitment for teaching staff usually has several stages and standardization of assessment in selection proces. In order for the process of selecting educators to be carried out objectively, a support system is need to carry out the assessment process. This study applies the Fuzzy K-Nearest Neighbor (FK-NN) method for the classification process in determining prospective educators who pass or not. Data classification is a new data or object grouping into classes or labels based on certain attributes. The application of the FK-NN method has several stages, namely weighting the criteria, then calculating the closeness of the test data and training data, finding the value of k-nearest neighbors between the training data and testing data and determining the membership of each data. Tests were carried out using the Confusion matrix method on several variations of the k value where the highest percentage was obtained from the value of k = 5. The test results for all k values obtained an average accuracy rate of 89.22%, 89.22% precision and 82.45% recall with 114 training data and 50 test data. Based on the average value of the test results, it can be concluded that the FK-NN method is feasible and good to use for the selection of educators with the classification of pass or not.