Next-Gen Talent Matching System: Innovating Recruitment with AI-Driven JD and CV Matching

Nikhil Modi; Aaditi Indalkar; Aryan Kapole; Saara Khamkar; Madhavi A. Indalkar1

1

Publication Date: 2025/01/08

Abstract: This study introduces the Next-Gen Talent Matching System, an innovative JD-based CV filtering web application designed to transform the recruitment process by leveraging Large Language Models (LLMs) and OpenAI technologies. Unlike traditional systems that rely on skill-based c filtering, this system focuses on job description (JD)-based filtering, providing greater accuracy and relevance in candidate selection. By enabling users to securely submit CVs, the system stores data in a MongoDB database, allowing HR administrators to access and match CVs based on semantic analysis. Using LLMs, the system analyses job descriptions and CVs to rank candidates according to how well they align with the job requirements, taking into account skills, experience, and qualifications. This approach enhances the efficiency of the recruitment process by automating initial screening, reducing human bias, and providing real-time feedback to candidates. The Next-Gen Talent Matching System not only improves the quality of candidate shortlisting but also integrates with existing HR platforms and scales to handle both small and large recruitment needs. Through its AI- driven, data-centric approach, the system serves as a powerful tool for modern recruitment, significantly reducing the time and effort required by HR professionals while ensuring more accurate and unbiased hiring decisions.

Keywords: JD-based Filtering, LLMs, OpenAI, AI-driven Recruitment, Semantic Analysis, Bias Reduction, Automated Candidate Matching.

DOI: https://doi.org/10.5281/zenodo.14608655

PDF: https://ijirst.demo4.arinfotech.co/assets/upload/files/IJISRT24DEC1980.pdf

REFERENCES

  1. Gupta and P. Bhalla, "A study of E-Recruitment From the Perspective of Job Applicants," International Journal of Advanced Research in Computer Science, vol. 9, no. 1, pp. 150-156, 2018.
  2. P. Srivastava and N. Rathod, "An efficient algorithm for ranking candidates in e-recruitment system," International Journal of Computer Applications, vol. 125, no. 11, pp. 25-29, 2015.
  3. S. D. Arora and R. Dhiman, "Artificial Intelligence in Human Resource Management," Journal of Strategic Human Resource Management, vol. 8, no. 3, pp. 45-52, 2019.
  4. J. Singh and S. Patel, "AI Based Suitability Measurement and Prediction Between Job Description and Job Seeker Profiles," in Proceedings of the International Conference on Artificial Intelligence and Machine Learning, Jaipur, India, 2020, pp. 180188.
  5. R. Kumar and A. Gupta, "Job opportunities for LIS professionals in India: A study based on Online Job portals," Journal of Library and Information Science, vol. 10, no. 2, pp. 85-95, 2020.
  6. S. Sharma and M. Mehta, "Real-Time Resume Screening Using NLP and Token-Based Indexing," Journal of Emerging Trends in Computing and Information Sciences, vol. 7, no. 4, pp. 101-107, 2016.
  7. T. Kumar and S. Srivastava, "Resume Classification System using Natural Language Processing and Machine Learning Techniques," International Journal of Computational Intelligence and Information Security, vol. 5, no. 2, pp. 38-44, 2021.
  8. Lang Chain, "Lang Chain Documentation," accessed Oct. 3, 2024. [Online]. Available: https://python.langchain.com/
  9. MongoDB, Inc., "MongoDB Documentation," accessed Oct. 3, 2024. [Online]. Available: https://docs.mongodb.com/ AUTHORS