RHEM: A Robust Hybrid Ensemble Model for Students’ Performance Assessment on Cloud Computing Course

Abstract

Creating tools, such as a prediction model to assist students in a traditional or virtual setting, is an essential activity in today's educational climate. The early stage towards incorporating these predictive models using techniques of machine learning focused on predicting the achievement of students in terms of the grades obtained. The research aim is to propose a robust hybrid ensemble model (RHEM) that can warn at-risks students (on Cloud Computing course) of their likely outcomes at the early semester assessment. We hybridised four renowned single algorithms-Naïve Bayes, Multilayer Perceptron, k-Nearest Neighbours, and Decision Tablewith four well-established ensemble algorithms-Bagging, RandomSubSpace, MultiClassClassifier, and Rotation Forestwhich produced 16 new hybrid ensemble classifier models. Hence, we have thoroughly and rigorously built, trained, and tested 24 models all together. The experiment concluded that the Rotation Forest + MultiLayer Perceptron model was the best performing model based on the model evaluation in terms of Accuracy (91.70%), Precision (86.1%), F-Score rate (87.3%), and Receiver Operating Characteristics Area detection (98.6%). Our research will help students identify their likely final grades in terms of whether they are excellent, very good, good, pass, or fail, and, thus, transform their academic conduct to achieve higher grades in the final exam accordingly.

revisión sobre la predicción del rendimiento académico mediante métodos de ensamble

“…Access to internet, Age, Economic dependence, Employment status, Ethnicity, Family Highest Education Level, Family income, Family size, Gender, Health status, House to university distance, Lives in town or village, Marital Status, Nationality, Parents job, Parents occupation, Parents qualification, Parent status, Total income [17], [22], [23], [26], [28]- [31], [35], [38], [41]- [43], [46], [48]- [55], [57]- [60], [63]- [65], [67], [68], [70]- [77] Leonardo…”

“…Table 4 shows the variables found that belong to the factor and the authors who used some of these for the development of their models. [22], [23], [26], [28]- [30], [35], [38]- [40], [42]- [44], [46], [49]- [52], [55], [57], [58], [60], [61], [63]- [68],…”

“…However, more recent algorithms are being applied, as is the case of Kostopoulos [57], which develops the so-called Rotation Forest and LogitBoost, obtaining these two better results than the classic algorithms and the other applied ensemble algorithms. Sakri [63] also uses Rotation Forest for the development of models, and obtains the highest accuracy within the algorithms applied in isolation. On the other hand, Jayaprakash [54] uses LogitBoost, with which it obtains the highest accuracy within the algorithms developed for predictions.…”

Predicting Academic Performance Using an Efficient Model Based on Fusion of Classifiers

“…Voting is also known for its heterogeneous nature where classifiers comprise different algorithms which are used to predict the final outcome. It creates two or more models and each of them make their predictions [36]. It is based on an aggregating network that is used to determine the weights' mean.…”