Predicting MA Ummu Qora students’ university admission with SVM and KNN

View at publisher Summarise with VIRAT
Authors: Angga Pramadjaya, Asep Erlan Maulana, Susanto, Ibnu Sina, Yunus, Achmad Chaerul Muslim, Jamaaluddin, Didik Iswadi
Cited by: 0
References: 11

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Student graduation for state universities is an important element for assessing school accreditation. Graduation from state universities for good achievement takes a normal time of 3 years from entering high school, but in reality many students do not graduate from state universities. Many factors cause failure to graduate from state universities, including internal and external factors. In this study, a classification method will be applied with the support vector machine algorithm and k-nearest neighbor based on particle swarm optimization to find the best method for classifying student data at the UMMU Qora Islamic high school. With attributes of age, gender, average report card grades, UAN, parental education, number of siblings. The results of the study produced the k-nearest neighbor method with a value of k=3 having a higher level of accuracy than the support vector machine and k-nearest neighbor algorithms with values of K5, K7, the best K-3 algorithm with an accuracy value of 88.70%, while the lowest accuracy value is in the support vector machine algorithm, which is 86.79%. The best precision value is the support vector machine algorithm with a value of 90.62% compared to the K-NN K3, K5, K7 algorithms. And the algorithm with the best recall value is the K-NN K7 algorithm with a value of 91.3%. The attribute that has the most influential weight on the prediction results of entering state universities in the k-nearest neighbor algorithm with a value of K3 is based on the average report card value, parents’ jobs, and parents’ education.

Fields of Study & Subjects

Data Mining and Machine Learning Applications Online Learning and Analytics Artificial Intelligence in Healthcare

Publication details

Journal / source
AIP conference proceedings
Volume
3480
Pages
040031–040031
Publication date
1 January 2026
Language
EN