Work

Student Performance Prediction using Support Vector Machine

Year: 2022
Type: article
Abstract: Predicting students' academic progress is critical in a university setting for early diagnosis of at-risk pupils. The goal of this work is to offer data mining models that use classification methods based on Support Vector Machine (SVM) algorithms to forecast students' academic accomplishment after a preparatory year, as well as to select the optimal approach. Based on graduation CGPA, students' academic achievement is classified as High, Average, or Below Average, and these classifications are applied to a newly produced dataset.
Language: English
Open Access status: diamond
OpenAlex ID: W4281262070
FWCI: 0.473
Cites: 8
Cited by: 5
Related to: 10