Ensemble Machine Learning to Predict and Feature Engineering to Identify Factors for Academic-Success

DOI

10.2991/978-94-6463-314-6_28How to use a DOI?

Keywords

Education; Random Forest; SVM; Hugging face; MLOps

Abstract

This paper presents academic-success, a machine learning predictor system designed to forecast student dropout rates or academic success and offer tailored interventions and support. The work encompasses the design of a predictive model and the provision of resources to integrate the model into existing student support systems within educational institutions.

The proposed predictive model is implemented and incorporating feature engineering, Importance analysis is carried out. The “enrolled class” is included for training and validation of the predictive model and also for the Importance analysis. The experiments are done using the ensemble learning and Support Vector Classifier (SVC). According to the experimental results for Area Under Curve in Receiver Operating Characteristics (ROC) curve, inclusion of the “Enrolled class” gave improved results for both ensemble learning (0.91) as well as SVC (0.86). Feature importance analysis using Leave One Feature Out (LOFO) and SHapley Additive exPlanations (SHAP) gave interesting results on the significance of education/occupation of the mother vs the father’s, importance of a steady approach towards course enrollment and the role of scholarships. This gives an added impetus to focus on women’s education and empowerment to improve the society through the next generation.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Syed Affan Daimi
AU  - Asma Iqbal
PY  - 2023
DA  - 2023/12/21
TI  - Ensemble Machine Learning to Predict and Feature Engineering to Identify Factors for Academic-Success
BT  - Proceedings of the International e-Conference on Advances in Computer Engineering and Communication Systems (ICACECS 2023)
PB  - Atlantis Press
SP  - 275
EP  - 285
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6463-314-6_28
DO  - 10.2991/978-94-6463-314-6_28
ID  - Daimi2023
ER  -