Resume screening Using Machine Learning

Resume screening Using Machine Learning

1.Duddupudi Lasya Sri Priya

Department of Computer Science in AIML Sasi Institute of technology and Engineering lasya.duddupudi@sasi.ac.in

2. Adusumilli Kavya

Department of Computer Science in AIML Sasi Institute of technology and Engineering kavya.adusumilli@sasi.ac.in

3. Dodla Poorna Satya Sri

Department of Computer Science in AIML Sasi Institute of technology and Engineering satyasri.dodla@sasi.ac.in

4. Thotakura Satya Sri

Department of Computer Science in AIML Sasi Institute of technology and Engineering satyasri.thotakura@sasi.ac.in

K. Suresh

Assistant Professor, CSE-AIML

Institution: Sasi Institute of Technology and Engineering

Abstract

Due to the increasing number of job applications for a specific position, the recruitment process is becoming more challenging for organizations. Manual resume screening is a traditional process in which recruiters have to screen a large number of resumes for a specific position. This is a time-consuming and inefficient process, and sometimes human errors are involved in this process. To overcome such problems, this project proposes a system for automated resume screening using Natural Language Processing (NLP) and Machine Learning (ML) techniques. Important information is obtained from resumes using NLP techniques and compared with the job requirements to find the most suitable candidate for a specific position. Various text preprocessing techniques are used for resume data. Semantic embeddings are obtained using Sentence-BERT (SBERT) for candidate selection. Cosine similarity is used to find the relevance between resumes and job requirements. Based on the results obtained from this process, candidates are ranked, and a list of relevant candidates is obtained. This system is implemented using Python for efficient resume analysis. From the experimental results, it is clear that this system is more efficient in resume screening..

KEYWORDS: Resume Screening, Natural Language Processing, Machine Learning, SBERT, Cosine Similarity, Recruitment Automation.