This project investigates the relationship between students' preadmission academic profile and final academic performance. Predicting Students performance beforehand can be very beneficial for educational institutions to improve their teaching quality. Further, the importance of several different attributes, or "features" is considered to determine which of these correlate with student performance. This project proposes to predict students’ performance by evaluating their academic details. Data preprocessing was done to remove the results of rusticated and expelled students. Results obtained by comparing SVM with other ML techniques such as KNN, Decision trees, and linear Regression show that SVM outperforms other ML algorithms. The parameters of the SVM algorithm(kernel) were also tuned to improve its accuracy.