The goal of data mining (DM) approaches is to extract insights that can be used to improve classroom instruction from a big dataset including information on individual students. The dataset in question contains personal information about the pupils. Within the educational sector, there has been an increase in the level of interest in DM techniques. EDM is quickly becoming a vital tool in the classroom because to its advantageous decision-making and prediction abilities. The ability of EDM models to make predictions about the future performance of students based on data already collected from those pupils is what gives these models their worth. The ability to foresee students’ academic success has excited the curiosity of scholars and universities interested in classifying students’ academic achievements at various educational levels. To help both students and teachers reach their maximum potential, a student performance evaluation methodology is essential. This section contains machine learning and feature selection-based methodology to Forecast Student’s Employability and Academic Success. PSO based Fuzzy SVM RBF algorithm is achieving 98% accuracy to Forecast Student’s Employability and Academic success.