International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 09 | Sep 2024
p-ISSN: 2395-0072
www.irjet.net
Automated Resume Shorlisting Sanjay 1 Tech Mahindra ---------------------------------------------------------------------***--------------------------------------------------------------------integration and real-world effectiveness. The subsequent Abstract - This paper presents an automated solution for
sections delve into methodologies, experiments, and results, showcasing the approach's efficacy. The research contributes to HR technology, enabling data-driven hiring decisions and fostering efficient, unbiased recruitment processes.
the candidate selection process in online recruitment using the NLP. In an era where traditional hiring practices prove less effective, our approach addresses the challenges posed by the growing of unstructured resumes. By employing TFIDF Vectorizer, Truncated SVD, and Cosine Similarity, it accurately evaluates resumes' relevance to job descriptions. Integration of NLTK and PDFMiner ensures precise text processing, handling various resume formats. The system's user-friendly interface, developed with Flask, simplifies interaction, allowing seamless uploading and analysis of resumes. Real-world evaluations demonstrate its efficiency, significantly reducing manual screening efforts. This approach stands as a comprehensive and practical method, showcasing the power of NLP in optimizing the recruitment process for organizations.
2. LITERATURE SURVEY The implementation of Natural Language Processing (NLP) techniques in various domains has significantly revolutionized the way data is processed and interpreted. In the realm of online examinations, NLP has enabled the assessment of descriptive answers, moving beyond the constraints of traditional multiple-choice formats [1]. This shift has been facilitated by employing Python and Django for implementation, providing students with a digital, errorcorrecting experience and ensuring instant evaluation. The versatility of this approach is enhanced by its facultycustomizable questions and keyword-based answer evaluation, leading to a dashboard-driven user interface. Additionally, this innovation has paved the way for the detection of academic dishonesty, thereby enhancing the integrity of examinations [1].
Key Words:— TF-IDF Vectorizer, Truncated SVD, and Cosine Similarity NLTK, pdf miner, flask
1.INTRODUCTION The paper titled "Automated Resume Shortlisting Using NLP: A Comprehensive Approach with TF-IDF Vectorizer, Truncated SVD, Cosine Similarity, NLTK, PDF Miner, and Flask" addresses the challenges faced by HR professionals and recruiters in sorting through a large volume of resumes to identify suitable candidates. The study introduces an innovative solution by integrating Natural Language Processing (NLP) techniques and machine learning algorithms, utilizing advanced tools like TF-IDF Vectorizer, Truncated SVD, Cosine Similarity, NLTK, PDF Miner, and Flask.
In the domain of requirements extraction, heuristic rules have been explored to extract conceptual models from natural language requirements [2]. This involves identifying concepts through nouns and relationships through verbs, utilizing rules such as compound nouns forming concepts and hierarchical relationships indicated by verbs like 'to be'. This comprehensive approach ensures the extraction of relevant models from natural language requirements, contributing to effective requirement analysis and system design.
The research focuses on automating the resume shortlisting process, making it efficient and accurate. TF-IDF Vectorizer converts resume text into numerical vectors, capturing candidate qualifications. Truncated SVD reduces data dimensionality for faster analysis, while Cosine Similarity matches job requirements with applicant skills, ensuring precise shortlisting. NLTK handles language processing tasks, and PDFMiner extracts text from PDF resumes, broadening document format compatibility. Flask, a Python web framework, creates an interactive interface for userfriendly recruitment.
In the context of automated resume shortlisting, NLP algorithms have been instrumental in parsing resumes and social profiles automatically, transforming unstructured data into a structured format [5]. This innovation addresses the challenge of extracting structured information from diverse resume formats. The ranking process, which includes attributes such as education, experience, and communication skills, is handled efficiently through this automated system. By employing techniques such as cosine similarity and machine learning models like K-Nearest Neighbor and Support Vector Machine, the system achieves accurate and efficient automated ranking for client companies [5] [10].
By automating resume screening, organizations save time and effort in initial recruitment stages. It guarantees fair evaluation, promoting diversity and inclusivity. The paper emphasizes practical implications, demonstrating technical
© 2024, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 458