Analyzing Student Academic Achievement Using Machine Learning Techniques at Senior High School Darunnajah Jakarta
Education provides a very important role in improving the quality of life in society in a country. With a large number of students in each class, it can cause the material to not be delivered properly. Therefore, it is necessary to group students based on their learning ability. The data used was ob...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universitas Teknologi Akba Makassar, Lembaga Penelitian dan Pengabdian Masyarakat
2024-06-01
|
| Series: | Inspiration |
| Subjects: | |
| Online Access: | https://ojs.unitama.ac.id/index.php/inspiration/article/view/81 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583811683057664 |
|---|---|
| author | Supriadi Panggabean Wahyu Joko Saputro |
| author_facet | Supriadi Panggabean Wahyu Joko Saputro |
| author_sort | Supriadi Panggabean |
| collection | DOAJ |
| description | Education provides a very important role in improving the quality of life in society in a country. With a large number of students in each class, it can cause the material to not be delivered properly. Therefore, it is necessary to group students based on their learning ability. The data used was obtained from Senior High School (SMA) Darunnajah Jakarta. Darunnajah High School Jakarta is one of the educational institutions under the auspices of Darunnajah Islamic Boarding School. Data mining techniques with classification methods are proposed to predict student performance in class. The results of student classification can be used as a reference in providing material according to their learning ability. The aim of this research is to ascertain the optimal classification algorithm and pinpoint the key factors influencing students' academic standing. Various classification methods, including logistic regression, KNN, and SVM, were employed in this study. The performance of these models was assessed using diverse metrics such as the f1 score, ROC curve, and performance matrix. Ultimately, the SVM algorithm demonstrated the highest accuracy, achieving an 84% accuracy rate compared to KNN and logistic regression. |
| format | Article |
| id | doaj-art-bf245e1453d548609d176de25b06aa7d |
| institution | Kabale University |
| issn | 2088-6705 2621-5608 |
| language | English |
| publishDate | 2024-06-01 |
| publisher | Universitas Teknologi Akba Makassar, Lembaga Penelitian dan Pengabdian Masyarakat |
| record_format | Article |
| series | Inspiration |
| spelling | doaj-art-bf245e1453d548609d176de25b06aa7d2025-01-28T05:47:58ZengUniversitas Teknologi Akba Makassar, Lembaga Penelitian dan Pengabdian MasyarakatInspiration2088-67052621-56082024-06-0114112514310.35585/inspir.v14i1.8181Analyzing Student Academic Achievement Using Machine Learning Techniques at Senior High School Darunnajah JakartaSupriadi Panggabean0Wahyu Joko Saputro1Universitas DarunnajahUniversitas DarunnajahEducation provides a very important role in improving the quality of life in society in a country. With a large number of students in each class, it can cause the material to not be delivered properly. Therefore, it is necessary to group students based on their learning ability. The data used was obtained from Senior High School (SMA) Darunnajah Jakarta. Darunnajah High School Jakarta is one of the educational institutions under the auspices of Darunnajah Islamic Boarding School. Data mining techniques with classification methods are proposed to predict student performance in class. The results of student classification can be used as a reference in providing material according to their learning ability. The aim of this research is to ascertain the optimal classification algorithm and pinpoint the key factors influencing students' academic standing. Various classification methods, including logistic regression, KNN, and SVM, were employed in this study. The performance of these models was assessed using diverse metrics such as the f1 score, ROC curve, and performance matrix. Ultimately, the SVM algorithm demonstrated the highest accuracy, achieving an 84% accuracy rate compared to KNN and logistic regression.https://ojs.unitama.ac.id/index.php/inspiration/article/view/81classificationstudents performancedata miningeducation |
| spellingShingle | Supriadi Panggabean Wahyu Joko Saputro Analyzing Student Academic Achievement Using Machine Learning Techniques at Senior High School Darunnajah Jakarta Inspiration classification students performance data mining education |
| title | Analyzing Student Academic Achievement Using Machine Learning Techniques at Senior High School Darunnajah Jakarta |
| title_full | Analyzing Student Academic Achievement Using Machine Learning Techniques at Senior High School Darunnajah Jakarta |
| title_fullStr | Analyzing Student Academic Achievement Using Machine Learning Techniques at Senior High School Darunnajah Jakarta |
| title_full_unstemmed | Analyzing Student Academic Achievement Using Machine Learning Techniques at Senior High School Darunnajah Jakarta |
| title_short | Analyzing Student Academic Achievement Using Machine Learning Techniques at Senior High School Darunnajah Jakarta |
| title_sort | analyzing student academic achievement using machine learning techniques at senior high school darunnajah jakarta |
| topic | classification students performance data mining education |
| url | https://ojs.unitama.ac.id/index.php/inspiration/article/view/81 |
| work_keys_str_mv | AT supriadipanggabean analyzingstudentacademicachievementusingmachinelearningtechniquesatseniorhighschooldarunnajahjakarta AT wahyujokosaputro analyzingstudentacademicachievementusingmachinelearningtechniquesatseniorhighschooldarunnajahjakarta |