A MACHINE LEARNING APPROACH TO STUDENT ACADEMIC PERFORMANCE ANALYSIS USING LINEAR REGRESSION

International Journal of Computer Science (IJCS) Published by SK Research Group of Companies (SKRGC)

Abstract

Student academic performance analysis is an important application of machine learning in the education sector. Educational institutions collect academic data such as attendance percentage, internal assessment marks, assignment scores, and previous semester results. Analyzing these attributes can help identify performance patterns and estimate students’ future academic outcomes. Traditional result analysis methods mainly rely on manual calculations and descriptive statistics, which may not provide sufficient predictive insights. This paper proposes a student performance analysis system using Linear Regression, a supervised machine learning algorithm. The system uses historical student data to predict final examination marks based on selected academic attributes. The methodology includes data collection, preprocessing, exploratory data analysis, model training, prediction, and evaluation. The model is evaluated using Mean Absolute Error, Mean Squared Error, Root Mean Squared Error, and the coefficient of determination. A sample student dataset is used to illustrate the proposed implementation. The system can assist teachers in identifying academic trends, estimating expected performance, and planning suitable learning interventions. The study highlights the usefulness of linear regression as an interpretable baseline model for educational data analysis.

References

1. Romero, C. and Ventura, S. 2010. “Educational Data Mining: A Review of the State of the Art.” IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews 40(6), pp. 601–618.
2. Cortez, P. and Silva, A. 2008. “Using Data Mining to Predict Secondary School Student Performance.” In Proceedings of the 5th Annual Future Business Technology Conference (FUBUTEC 2008), pp. 5–12.
3. Baker, R. S. and Inventado, P. S. 2014. “Educational Data Mining and Learning Analytics.” In Larusson, J. A. and White, B. (eds.), Learning Analytics: From Research to Practice. Springer, pp. 61–75.
4. James, G., Witten, D., Hastie, T., and Tibshirani, R. 2021. An Introduction to Statistical Learning: With Applications in R, 2nd ed. Springer.

Keywords

Data mining, linear regression, machine learning, student performance.