Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal INSYPRO (Information System and Processing)
Abdullah, Patmayanti Kartini
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Aplikasi Mobile Forecasting Prestasi Rendah Mahasiswa dengan Algoritma Support Vector Machine (SVM) pada Fakultas Sains dan Teknologi UIN Alauddin Makassar Wahyuni, Sri; Baharuddin, Hastuti; Abdullah, Patmayanti Kartini
Jurnal INSYPRO (Information System and Processing) Vol 8 No 2 (2023)
Publisher : Prodi Sistem Informasi UIN Alauddin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24252/insypro.v8i2.43479

Abstract

Achievement is the value of students' learning activity achievements given by the lecturer in the relevant course based on previously determined assessment criteria. This research aims to develop a forecasting information system for low achieving students which can help identify which students have low achievement. The algorithm used is Support Vector Machine (SVM) to model the relationship between variables related to low student achievement. The dataset used comes from alumni from the 2015-2017 class, while the sample for forecasting student achievement uses the 2020 and 2021 classes. The research results show that in creating a forecasting information system for low achieving students, factors such as 1st semester GPA, 2nd semester GPA, 2nd semester GPA 3, 2nd semester credits, 3rd semester credits, semester 1-3 absences, as well as student participation in competitions and organizations have a significant influence on low student achievement. Accuracy shows that the Keras library has an average accuracy of around 83%, while scikit-learn has an average accuracy of around 82%. With these accuracy values, it can be concluded that this system has good performance in predicting low achieving students.
Co-Authors Hastuti Baharuddin, Hastuti Sri Wahyuni