Student performance evaluation, which provides informative data about each student's learning outcomes and overall academic development, is an essential part of education. Predicting student test results has grown in importance as a research area with the potential to revolutionise educational practises and assist personalised learning approaches. By accurately forecasting student performance, educators can identify those who are at risk of failing and use early intervention strategies. Additionally, tailored training is made possible through test result prediction, which enhances the learning process overall. This is done by tailoring teaching methods and course content to each student's needs. Machine learning and statistical methods are most typically utilised to assess the collected data and develop prediction models. Regression models, for instance, can be used to find connections between the anticipated test score (dependent) and variables like past test results or other characteristics (independent). This strategy makes it feasible for early intervention, personalised instruction, and informed decision-making, all of which enhance student learning outcomes.