Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2025
|
| Online Access: | https://doi.org/10.5281/zenodo.15595362 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866901569461551104 |
|---|---|
| author | WADA, OJONUGWA |
| author_facet | WADA, OJONUGWA |
| contents | <p>In recent years, machine learning has emerged as a transformative tool in education, providing data-driven insights into student performance and allowing for proactive interventions. This study uses supervised machine learning models to investigate how behavioral habits, demographic traits, and lifestyle choices influence academic attainment. This study investigates the association between non-academic activities and test results using a dataset of 1,000 students that includes variables such as study hours, sleep duration, mental health assessment, internet quality, and others. Four regression models were trained and evaluated using RMSE and R2 Score measures: linear regression, decision tree regression, random forest regression, and gradient boosting regression. The Linear Regression model fared better than others, with an RMSE of 5.14 and a R² Score of 0.90, indicating high predictive capacity. A special interactive prediction interface was created to put these findings into practice for educators, parents, and students. This work contributes to the emerging field of educational data mining by including holistic behavioral aspects into academic performance modeling, hence facilitating the creation of individualized, context-aware educational assistance systems.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_15595362 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | DESIGN AND DEVELOPMENT OF A DECISION SUPPORT SYSTEM FOR PREDICTING STUDENT ACADEMIC PERFORMANCE WADA, OJONUGWA <p>In recent years, machine learning has emerged as a transformative tool in education, providing data-driven insights into student performance and allowing for proactive interventions. This study uses supervised machine learning models to investigate how behavioral habits, demographic traits, and lifestyle choices influence academic attainment. This study investigates the association between non-academic activities and test results using a dataset of 1,000 students that includes variables such as study hours, sleep duration, mental health assessment, internet quality, and others. Four regression models were trained and evaluated using RMSE and R2 Score measures: linear regression, decision tree regression, random forest regression, and gradient boosting regression. The Linear Regression model fared better than others, with an RMSE of 5.14 and a R² Score of 0.90, indicating high predictive capacity. A special interactive prediction interface was created to put these findings into practice for educators, parents, and students. This work contributes to the emerging field of educational data mining by including holistic behavioral aspects into academic performance modeling, hence facilitating the creation of individualized, context-aware educational assistance systems.</p> |
| title | DESIGN AND DEVELOPMENT OF A DECISION SUPPORT SYSTEM FOR PREDICTING STUDENT ACADEMIC PERFORMANCE |
| url | https://doi.org/10.5281/zenodo.15595362 |