Student Performance Analysis using Machine Learning

TITLE	Student Performance Analysis using Machine Learning
ABSTRACT	Effectively forecasting the performance of students is another key feature of contemporary educational analytics, which establishes the ability of educational institutions to recognize the learning gaps, offer necessary interventions in time and enhance the overall performance. The proposed study introduces a machine learning-based model of academic performance analysis and performance prediction of students based on the history of the student,including passing grades on past tests, absenteeism and other characteristics. There were preprocessing processes including data cleaning, feature encoding, and normalization in order to maintain quality of the data and make the model reliable. A range of supervised learning algorithms was applied, and these include Linear Regression, Random Forest, and Gradient Boosting Regressor, being assessed with the help of such metrics as the accuracy, Root Mean Squared Error (RMSE), and R 2 score, among others. Experimental results indicated that the ensemble-based models especially Gradient Boosting had better predictive performance than the traditional regressions methods. These results provide an indication of the role of machine learning in data mining of education in that decision making could be made based on data by the educators. When institutions use predictive analytics, they can intervene early on to help at-risk students, create learning plans to best accommodate specific student needs, and ultimately achieve higher academic success outcomes.
AUTHOR	Prateek K, Raimath Ali, Rajendra Ganapati Naik Department of Masters of Computer Applications, CMR Institute of Technology, Bengaluru, India
PUBLICATION DATE	2025-09-08
VOLUME	12
DOI	DOI:10.15680/IJARETY.2025.1204073
PDF	73_Student Performance Analysis using Machine Learning.pdf
KEYWORDS

Article

Email

[email protected]