Predicting the eligibility of placement for students using data mining

Abstract

Every educational institution uses campus placement to help students achieve their goals. Data mining techniques are frequently used in the educational system, which employs a variety of learning methods and approaches. A predictive model is built based on academic and extracurricular achievements to determine which category of placements (dream businesses, super dream companies, and mass recruiter companies) students are suitable for. Admission and the name of the institution are heavily influenced by placements. The main goal of this paper is to analyze previous year's applicant data in order to predict current students' placement chances and help institutions increase their placement percentage . Our project's main goal is to determine location using student data and to implement KNN models, logistic regression models, random forest models, and SVM models. Our project represents the candidate placement classification provided in the available data set. These algorithms predict the results on their own, and then we compare the algorithms' efficiency based on thedataset. This model assists a company's position cell in screening potential candidates and focusing and improving their technical and soft skills at regular intervals.