Student Dropout Prediction for University with High Precision and Recall
Since a high dropout rate for university students is a significant risk to local communities and countries, a dropout prediction model using machine learning is an active research domain to prevent students from dropping out. However, it is challenging to fulfill the needs of consulting institutes a...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/10/6275 |
| _version_ | 1827742129044062208 |
|---|---|
| author | Sangyun Kim Euteum Choi Yong-Kee Jun Seongjin Lee |
| author_facet | Sangyun Kim Euteum Choi Yong-Kee Jun Seongjin Lee |
| author_sort | Sangyun Kim |
| collection | DOAJ |
| description | Since a high dropout rate for university students is a significant risk to local communities and countries, a dropout prediction model using machine learning is an active research domain to prevent students from dropping out. However, it is challenging to fulfill the needs of consulting institutes and the office of academic affairs. To the consulting institute, the accuracy in the prediction is of the utmost importance; to the offices of academic affairs and other offices, the reason for dropping out is essential. This paper proposes a Student Dropout Prediction (SDP) system, a hybrid model to predict the students who are about to drop out of the university. The model tries to increase the dropout precision and the dropout recall rate in predicting the dropouts. We then analyzed the reason for dropping out by compressing the feature set with PCA and applying K-means clustering to the compressed feature set. The SDP system showed a precision value of 0.963, which is 0.093 higher than the highest-precision model of the existing works. The dropout recall and F1 scores, 0.766 and 0.808, respectively, were also better than those of gradient boosting by 0.117 and 0.011, making them the highest among the existing works; Then, we classified the reasons for dropping out into four categories: “Employed”, “Did Not Register”, “Personal Issue”, and “Admitted to Other University.” The dropout precision of “Admitted to Other University” was the highest, at 0.672. In post-verification, the SDP system increased counseling efficiency by accurately predicting dropouts with high dropout precision in the “High-Risk” group while including more dropouts in total dropouts. In addition, by predicting the reasons for dropouts and presenting guidelines to each department, the students could receive personalized counseling. |
| first_indexed | 2024-03-11T03:57:51Z |
| format | Article |
| id | doaj.art-967b82e7644c4cc2a6a7c51a93f144d7 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T03:57:51Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-967b82e7644c4cc2a6a7c51a93f144d72023-11-18T00:23:11ZengMDPI AGApplied Sciences2076-34172023-05-011310627510.3390/app13106275Student Dropout Prediction for University with High Precision and RecallSangyun Kim0Euteum Choi1Yong-Kee Jun2Seongjin Lee3Department of Informatics, Gyeongsang National University, Jinju-daero 501, Jinjusi 52828, Republic of KoreaResearch Center for Aircraft Parts Technology, Gyeongsang National University, Jinju-daero 501, Jinjusi 52828, Republic of KoreaDivision of Aerospace and Software Engineering, Gyeongsang National University, Jinju-daero 501, Jinjusi 52828, Republic of KoreaDepartment of AI Convergence Engineering, Gyeongsang National University, Jinju-daero 501, Jinjusi 52828, Republic of KoreaSince a high dropout rate for university students is a significant risk to local communities and countries, a dropout prediction model using machine learning is an active research domain to prevent students from dropping out. However, it is challenging to fulfill the needs of consulting institutes and the office of academic affairs. To the consulting institute, the accuracy in the prediction is of the utmost importance; to the offices of academic affairs and other offices, the reason for dropping out is essential. This paper proposes a Student Dropout Prediction (SDP) system, a hybrid model to predict the students who are about to drop out of the university. The model tries to increase the dropout precision and the dropout recall rate in predicting the dropouts. We then analyzed the reason for dropping out by compressing the feature set with PCA and applying K-means clustering to the compressed feature set. The SDP system showed a precision value of 0.963, which is 0.093 higher than the highest-precision model of the existing works. The dropout recall and F1 scores, 0.766 and 0.808, respectively, were also better than those of gradient boosting by 0.117 and 0.011, making them the highest among the existing works; Then, we classified the reasons for dropping out into four categories: “Employed”, “Did Not Register”, “Personal Issue”, and “Admitted to Other University.” The dropout precision of “Admitted to Other University” was the highest, at 0.672. In post-verification, the SDP system increased counseling efficiency by accurately predicting dropouts with high dropout precision in the “High-Risk” group while including more dropouts in total dropouts. In addition, by predicting the reasons for dropouts and presenting guidelines to each department, the students could receive personalized counseling.https://www.mdpi.com/2076-3417/13/10/6275dropout precisiondropout recallmachine learningimbalanced data processinghybrid methodbig data |
| spellingShingle | Sangyun Kim Euteum Choi Yong-Kee Jun Seongjin Lee Student Dropout Prediction for University with High Precision and Recall Applied Sciences dropout precision dropout recall machine learning imbalanced data processing hybrid method big data |
| title | Student Dropout Prediction for University with High Precision and Recall |
| title_full | Student Dropout Prediction for University with High Precision and Recall |
| title_fullStr | Student Dropout Prediction for University with High Precision and Recall |
| title_full_unstemmed | Student Dropout Prediction for University with High Precision and Recall |
| title_short | Student Dropout Prediction for University with High Precision and Recall |
| title_sort | student dropout prediction for university with high precision and recall |
| topic | dropout precision dropout recall machine learning imbalanced data processing hybrid method big data |
| url | https://www.mdpi.com/2076-3417/13/10/6275 |
| work_keys_str_mv | AT sangyunkim studentdropoutpredictionforuniversitywithhighprecisionandrecall AT euteumchoi studentdropoutpredictionforuniversitywithhighprecisionandrecall AT yongkeejun studentdropoutpredictionforuniversitywithhighprecisionandrecall AT seongjinlee studentdropoutpredictionforuniversitywithhighprecisionandrecall |