Predictive modelling and analytics of students’ grades using machine learning algorithms

Abstract

The outbreak of COVID-19 has caused significant disruption in all sectors and industries around the world. To tackle the spread of the novel coronavirus, the learning process and the modes of delivery had to be altered. Most courses are delivered traditionally with face-to-face or a blended approach through online learning platforms. In addition, researchers and educational specialists around the globe always had a keen interest in predicting a student’s performance based on the student’s information such as previous exam results obtained and experiences. With the upsurge in using online learning platforms, predicting the student’s performance by including their interactions such as discussion forums could be integrated to create a predictive model. The aims of the research are to provide a predictive model to forecast students’ performance (grade/engagement) and to analyse the effect of online learning platform’s features. The model created in this study made use of machine learning techniques to predict the final grade and engagement level of a learner. The quantitative approach for student’s data analysis and processing proved that the Random Forest classifier outperformed the others. An accuracy of 85% and 83% were recorded for grade and engagement prediction respectively with attributes related to student profile and interaction on a learning platform.

Artificial Intelligence: Its Role and Potential in Education

“…Although the data in the databases do not have meaning on their own, the connections revealed between the data processed by various data analysis methods can provide meaningful information. Researchers have recently turned to areas such as data mining, educational data mining and learning analytics, which are related to AI, in order to increase the efficiency of learning environments and analyze data such as student performance, class attendance, frequency of asking questions in order to predict possible failure situations (İbrahim & Rusli, 2007;Karabatak, 2008;Dekker, Pechenizkiy & Vleeshouwers, 2009;Mishra, Kumar & Gupta, 2014;Iatrellis, Savvasi, Fitsilis & Gerogiannis, 2021;Badal & Sungkur, 2023;Guleria & Sood, 2023;Chen & Zhai, 2023).…”

“…Iatrellis, Savvasi, Fitsilis & Gerogiannis (2021) stated that high-fidelity predictions were produced with a two-stage machine learning approach in their study to predict the results of students in higher education programs. Badal & Sungkur (2023) obtained successful results with 85% and 83% for grade and participation prediction with student profile and interaction-related attributes in their study to predict students' performance and analyze the features of the online learning platform. Çakıt & Dağdeviren (2022) compared the success of different machine learning approaches in their study to estimate the percentage of student placement based on the academic reputation of the university, the facilities of the city where the university is located, the facilities and cultural facilities of the university.…”

Predictive Model for Clustering Learning Outcomes Affected by COVID-19 Using Ensemble Learning Techniques

“…They compared several classifiers for the Majority Voting Ensemble. Badal and Sungkur (2022) developed a model to predict and analyze students' grades and engagement. In the data preprocessing stage, the Feature Encoding and the Synthetic Minority Over-Sampling Technique is used to manage the imbalanced classes and normalize the range of values of the data.…”

“…It helps researchers to improve the educational process and learning outcomes of students (Xu et al, 2021). Ensemble learning techniques have been used to enhance the predicting model of them (Badal & Sungkur, 2022;Karalar et al, 2021;Nachouki & Abou Naaj, 2022;Smirani et al, 2022).…”

Comparative Analysis of Regression Algorithms for Predicting Students' Overall Ratings

“…The scientific article [4] delves into the multifaceted realm of e-learning, student engagement, machine learning, and data utilization in education. It underscores the advantages of e-learning, particularly its flexibility and interactive capabilities through learning management systems (LMS), with a focus on asynchronous e-learning as a prevalent method.…”