GLoW SMOTE-D: Oversampling Technique to Improve Prediction Model Performance of Students Failure in Courses
The percentage of passing courses is dependent on the assistance provided to students. To ensure the effectiveness of these efforts, identifying students at risk of course failure as early as possible is crucial. The list of students at risk can be generated through academic performance prediction b...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10384376/ |
| _version_ | 1827376413803544576 |
|---|---|
| author | Susana Limanto Joko Lianto Buliali Ahmad Saikhu |
| author_facet | Susana Limanto Joko Lianto Buliali Ahmad Saikhu |
| author_sort | Susana Limanto |
| collection | DOAJ |
| description | The percentage of passing courses is dependent on the assistance provided to students. To ensure the effectiveness of these efforts, identifying students at risk of course failure as early as possible is crucial. The list of students at risk can be generated through academic performance prediction based on historical data. However, the number of students failing (7%) is significantly lower than the number succeeding (93%), resulting in a class imbalance that hampers performance. A widely adopted technique for addressing class imbalance issues is synthetic sample oversampling. Many oversampling techniques neglect discrete features, whereas the existing technique for discrete features treats all features uniformly and does not select samples as a basis for generating synthetic data. This limitation is capable of introducing noise and borderline samples. As a result, this study introduced a novel discrete feature oversampling technique called GLoW SMOTE-D. This technique accelerated the improvement of minority sample learning by performing multiple selections and multiple weighting in order to effectively reduce noise. Experimental results showed that this technique significantly enhanced the performance of students’ failure in the course prediction model when compared to various other techniques across a range of performance measures and classifiers. |
| first_indexed | 2024-03-08T12:09:32Z |
| format | Article |
| id | doaj.art-47200b076288420297524a90e57c2f58 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T12:09:32Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-47200b076288420297524a90e57c2f582024-01-23T00:06:07ZengIEEEIEEE Access2169-35362024-01-01128889890110.1109/ACCESS.2024.335156910384376GLoW SMOTE-D: Oversampling Technique to Improve Prediction Model Performance of Students Failure in CoursesSusana Limanto0https://orcid.org/0000-0002-5030-4921Joko Lianto Buliali1https://orcid.org/0000-0002-0990-3164Ahmad Saikhu2Informatics Department, Institut Teknologi Sepuluh Nopember, Surabaya, IndonesiaInformatics Department, Institut Teknologi Sepuluh Nopember, Surabaya, IndonesiaInformatics Department, Institut Teknologi Sepuluh Nopember, Surabaya, IndonesiaThe percentage of passing courses is dependent on the assistance provided to students. To ensure the effectiveness of these efforts, identifying students at risk of course failure as early as possible is crucial. The list of students at risk can be generated through academic performance prediction based on historical data. However, the number of students failing (7%) is significantly lower than the number succeeding (93%), resulting in a class imbalance that hampers performance. A widely adopted technique for addressing class imbalance issues is synthetic sample oversampling. Many oversampling techniques neglect discrete features, whereas the existing technique for discrete features treats all features uniformly and does not select samples as a basis for generating synthetic data. This limitation is capable of introducing noise and borderline samples. As a result, this study introduced a novel discrete feature oversampling technique called GLoW SMOTE-D. This technique accelerated the improvement of minority sample learning by performing multiple selections and multiple weighting in order to effectively reduce noise. Experimental results showed that this technique significantly enhanced the performance of students’ failure in the course prediction model when compared to various other techniques across a range of performance measures and classifiers.https://ieeexplore.ieee.org/document/10384376/Discreteimbalanced datasetoversamplingstudents’ failure |
| spellingShingle | Susana Limanto Joko Lianto Buliali Ahmad Saikhu GLoW SMOTE-D: Oversampling Technique to Improve Prediction Model Performance of Students Failure in Courses IEEE Access Discrete imbalanced dataset oversampling students’ failure |
| title | GLoW SMOTE-D: Oversampling Technique to Improve Prediction Model Performance of Students Failure in Courses |
| title_full | GLoW SMOTE-D: Oversampling Technique to Improve Prediction Model Performance of Students Failure in Courses |
| title_fullStr | GLoW SMOTE-D: Oversampling Technique to Improve Prediction Model Performance of Students Failure in Courses |
| title_full_unstemmed | GLoW SMOTE-D: Oversampling Technique to Improve Prediction Model Performance of Students Failure in Courses |
| title_short | GLoW SMOTE-D: Oversampling Technique to Improve Prediction Model Performance of Students Failure in Courses |
| title_sort | glow smote d oversampling technique to improve prediction model performance of students failure in courses |
| topic | Discrete imbalanced dataset oversampling students’ failure |
| url | https://ieeexplore.ieee.org/document/10384376/ |
| work_keys_str_mv | AT susanalimanto glowsmotedoversamplingtechniquetoimprovepredictionmodelperformanceofstudentsfailureincourses AT jokoliantobuliali glowsmotedoversamplingtechniquetoimprovepredictionmodelperformanceofstudentsfailureincourses AT ahmadsaikhu glowsmotedoversamplingtechniquetoimprovepredictionmodelperformanceofstudentsfailureincourses |