Revolutionizing Recruitment: A Comparative Study Of KNN, Weighted KNN, and SVM - KNN for Resume Screening

Abstract

In the recruitment process, continued screening assumes a fundamental part in distinguishing qualified contenders for a specific employment opportunity. A huge issue that scouts face is the tedious course of manual screening of resumes. To resolve this issue, this paper proposes the utilization of three ML calculations, in particular K-Nearest Neighbors (KNN), Weighted K-Nearest Neighbors (WKNN), and Support Vector Machine KNN (SVM KNN), for the mechanized screening of resumes. The dataset was manually created consisting of two segments that incorporate various classes like CA, advocate, engineering, and so forth, and the related resume portrayals. The dataset was utilized to prepare and assess the precision of the calculations. The trial concentrates on showing that Weighted KNN outperforms KNN and SVM KNN with an accuracy of 74%. The strategy can empower selection representatives to smooth out their enrollment interaction and distinguish qualified applicants rapidly and cost-effectively.