Comparative Between Three Machine Learning Algorithms to Predict and Improve Students’ Academic Performance

Autor: Bashiru Aliyu Sani, Samaila Baoku I.G, Bashir Jamilu Ahmed, Samaila Musa
Rok vydání: 2023
Zdroj: International Journal of Science for Global Sustainability. 8:4
ISSN: 2488-9229
DOI: 10.57233/ijsgs.v8i4.365
Popis: The greatest aim of every educational setup is giving the best educational experience and knowledge to the students. Discovering the students who need extra support and guidance so as to carry out the necessary actions to enhance their performance plays an important role in achieving that aim. In this research work, three machine learning algorithms have been used to build a classifier that can predict the performance of the students in higher institutions considering three Tertiary institutions which are: Federal University Dutsinma, Katsina State, Abdu Gusau Polytechnic Talata Mafara and College of Education Maru, Zamfara State. The machine learning algorithms includ: Support Vector Machine, Linear Regression and Stochastic Gradient descent algorithms. The models have been compared using the Mean Absolute Error, Mean Square Error and Root Mean Square Error classification accuracy. The dataset used to build the models is collected based on a survey given to the students and the students’ grade book. The support vector machine model achieved the best performance that is equal to 99.1%.
Databáze: OpenAIRE