Predicting Student Performance using Classification and Regression Trees Algorithm

Abstract

Now a days Internet and Web technologies providing students opportunities for flexible interactivity with study materials, peers and instructors. And also generating large amounts of usage data that can be processed and reveal behavioral patterns of study and learning. In this paper, to predict course performance we extracted data from a Moodlebased blended learning course and build a student model. Classification and Regression Trees (CART) decision tree algorithm was used to classify students and predict those at risk, based on the impact of four online activities: message exchanging, group wiki content creation, course files opening and online quiz taking. The correct classifications in results prove that the model is sensitive to categorize very specific groups at risk.

A Predictive Model using Machine Learning Algorithm in Identifying Student’s Probability on Passing Semestral Course

“…Predicting student performance gives helpful insights to the teachers particularly to the students who performed less in the class, on what necessary actions and assistance they can provide in terms of learning. The results of prediction provide helps to the institutions to change the and adjust the factors that contributed towards students past poor performance inside the classroom as stated by Krishna et al (2020).…”

“…In-depth study is being done in the field of educational data mining, according to Guleria et al (2014), to forecast student performance to act and prevent failure or dropout. According to Krishna et al (2020), Grade Point Average (GPA) or grades across assignments, class quizzes and exams, lab work, and attendance, as well as students' demographics, such as gender, age, and family background, and students' individual behaviors, such as beliefs, motivations, and learning strategies, are elements that have frequently been used by researchers in predicting student performance.…”

Cloud-Based Institutional Quality Assurance Model for a Local Higher Education Institution Using Data Mining Techniques

“…It helps in comprehending the fundamental reasons for performance variations by offering a clear visual representation of variable interactions. This clarity is essential for developing targeted interventions and improvement strategies in educational settings [9][10].…”

Accelerating the Move Towards Online Learning Through Cloud Platforms in Higher Education Sectors Using Smart Devices during COVID-19

“…Krishna et al constructed a student model by extracting data from Moodle to forecast their academic performance. The authors have used the Classification and Regression Trees (CART) decision tree algorithm to classify students and predict those at risk [10]. Christopher et al analyzed the various levels of cloud services and deployment models.…”