• Version
• Download 16
• File Size 703.95 KB
• File Count 1
• Create Date 24 July 2025
• Last Updated 24 July 2025

Automated Resume Screening Using Machine Learning

RONGALA RAJESH, KONKI CHARAN

Assistant Professor, 2MCA Final Semester, Master of Computer Applications, Sanketika Vidya Parishad Engineering College, Vishakhapatnam, Andhra Pradesh, India

Abstract:

The exponential growth of digital job applications has posed significant challenges for recruiters, who often face the daunting task of manually screening thousands of resumes to identify suitable candidates. This research addresses these challenges by proposing an automated resume classification system leveraging Natural Language Processing (NLP) and machine learning techniques. The proposed system integrates comprehensive text preprocessing, feature extraction using Term Frequency–Inverse Document Frequency (TF-IDF), and a One-vs-Rest K-Nearest Neighbors (KNN) classifier to categorize resumes into predefined job sectors. The methodology encompasses data collection and cleaning, exploratory data analysis with visualizations such as category distribution plots and word clouds, and model development and evaluation using accuracy and classification metrics. Experimental results demonstrate that the system effectively classifies resumes with promising accuracy, highlighting its potential to significantly reduce manual effort and improve the efficiency of the recruitment process. This study underscores the viability of deploying classical machine learning models for real-world human resource applications and sets the foundation for future enhancements using advanced deep learning and semantic text representation techniques.

Keywords: Automated resume screening, Machine learning, Natural language processing (NLP), Candidate      evaluation, Resume classification, Semantic similarity.