An Evolutionary Algorithm-Based Optimization Ensemble Learning Model for Predicting Academic Performance

The significant growth of the Massive Open Online Course (MOCC) over last decade has promoted the rise of the educational data mining era in online education domain. This situation has created an opportunity for an educator to utilize the available data from MOOCs to facilitate student learning and performance. Therefore, this research study aims to introduce three types of ensemble learning methods, which are stacking, boosting, and bagging, to predict student performance on the online learning data that contain 480 students with 17 features. These techniques have to include the evolutionary algorithm to select the optimal number of input parameter to build the ensemble learning model. As a result, the proposed stacking type ensemble classifier has shown the highest prediction accuracy of approximately 88% and Area Under the Curve (AUC) of approximately 0.85. Results by stacking ensemble classifier have outperformed other ensemble classifiers, bagging and boosting as well as base classifiers.

[1]  S. Dutta.  A Comparative Study of School Parent Satisfaction Predictors using different Classifiers , 2021, International Journal for Research in Applied Sciences and Biotechnology.

[2]  Nandini Nayar,et al.  EMT: Ensemble Meta-Based Tree Model for Predicting Student Performance in Academics , 2021 .

[3]  Utomo Pujianto,et al.  Students Academic Performance Prediction with k-Nearest Neighbor and C4.5 on SMOTE-balanced data , 2020, 2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI).

[4]  M. Alshurideh,et al.  Investigating a theoretical framework for e-learning technology acceptance , 2020, International Journal of Electrical and Computer Engineering (IJECE).

[5]  M. Kadastik,et al.  Evolutionary algorithms for hyperparameter optimization in machine learning for application in high energy physics , 2020, The European Physical Journal C.

[6]  Yi Wang,et al.  A comparative study of heterogeneous ensemble-learning techniques for landslide susceptibility mapping , 2020, Int. J. Geogr. Inf. Sci..

[7]  Han Cao,et al.  Predictive learning analytics using deep learning model in MOOCs’ courses videos , 2020, Education and Information Technologies.

[8]  Abel A. Castro Hoyos,et al.  Teaching Analytics: Current Challenges and Future Development , 2020, IEEE Revista Iberoamericana de Tecnologias del Aprendizaje.

[9]  Selma Ayşe Özel,et al.  Prediction of Students' Academic Success Using Data Mining Methods , 2018, 2018 Innovations in Intelligent Systems and Applications Conference (ASYU).

[10]  Selma Ayse Ozel,et al.  Prediction of Students' Academic Success Using Data Mining Methods , 2018 .

[11]  Mihaela van der Schaar,et al.  Progressive Prediction of Student Performance in College Programs , 2017, AAAI.

[12]  Ibrahim Aljarah,et al.  Mining Educational Data to Predict Student’s academic Performance using Ensemble Methods , 2016 .

[13]  Ajay Kaushik,et al.  Feature selection on educational data using Boruta algorithm , 2021, Int. J. Comput. Intell. Stud..

[14]  Pinaki Chakraborty,et al.  Students’ Performance Prediction Using Feature Selection and Supervised Machine Learning Algorithms , 2020 .