Authors : Srinidhi K S; Nischal V U; U Karthik; Manoj B P

Volume/Issue : Volume 10 - 2025, Issue 2 - February

Google Scholar : https://tinyurl.com/39hew5c3

Scribd : https://tinyurl.com/ycxhpuar

DOI : https://doi.org/10.5281/zenodo.14987553

Abstract : Selecting the ideal candidate is often a challenging endeavor time consuming, inefficient, and often influenced by biases. The Smart Hiring System is designed to change that. This platform streamlines recruitment by automating the most tedious parts of the process, from resume screening to candidate evaluations. Using machine learning, the system scans resume, picks out key qualifications, and matches them with job requirements ensuring the best-fit candidates move forward. The hiring journey is structured to be fair and efficient. Candidates first take an MCQ-based assessment, followed by a coding round and a descriptive evaluation, allowing recruiters to assess their real-world problem-solving skills. A standout feature is real-time speech-to-text transcription during HR interviews, making conversations smoother and evaluations more precise. To ensure fairness, bias mitigation techniques are integrated, reducing the impact of unconscious prejudices in hiring decisions. Secure email-based authentication safeguards user data, ensuring privacy and trust. By taking over repetitive tasks, the Smart Hiring System lets recruiters focus on what truly matters finding the right talent. The automated workflow not only reduces hiring time but also improves accuracy in matching candidates with roles. This research demonstrates how technology can transform hiring, making it faster, fairer, and more effective. In today’s competitive job market, a system like this isn’t just a convenience it’s a game changer for both recruiters and job seekers.

Keywords : Resume Parsing, Candidate Matching, Skill Extraction, MCQ Assessment, Technical Evaluation, Coding Test, HR Interview, Speech-to-Text Processing, Bias Mitigation, Secure Authentication, Automated Hiring, Job Recommendation, Recruitment Platform, Performance Evaluation, Data-Driven Hiring, Interview Transcription, Job Listings Management, Candidate Assessment.

References :

1. Kinger, S., Kinger, D., Thakkar, S. et al. Towards smarter hiring: resume parsing and ranking with YOLOv5 and DistilBERT. Multimed Tools Appl 83, 82069–82087 (2024).,doi.org/10.1007/s11042-024-18778-9.
2. Application of LLM Agents in Recruitment: A Novel Framework for Resume Screening [https://arxiv.org/abs/2401.08315].
3. C. N. Hang, C. Wei Tan and P. -D. Yu, "MCQGen: A Large Language Model-Driven MCQ Generator for Personalized Learning," in IEEE Access, vol. 12, pp. 102261-102273, 2024, doi: 10.1109/ACCESS.2024.3420709.
4. P. Babakhani, A. Lommatzsch, T. Brodt, D. Sacker, F. Sivrikaya and S. Albayrak, "Opinerium: Subjective Question Generation Using Large Language Models," in IEEE Access, vol. 12, pp. 66085-66099, 2024, doi: 10.1109/ACCESS.2024.3398553.
5. Feng, X., Zhao, Y., Zong, W. et al. Adaptive multi-task learning for speech to text translation. J AUDIO SPEECH MUSIC PROC. 2024, 36 (2024),doi.org/10.1186/s13636-024 00359-1.
6. Paiva, J.C., Leal, J.P. & Figueira, Á. Clustering source code from automated assessment of programming assignments. Int J Data Sci Anal (2024).https://doi.org/10.1007/s41060-024 00554.
7. Y. Zhou, Z. Wu, M. Zhang, X. Tian and H. Li, "TTS-Guided Training for Accent Conversion Without Parallel Data," in IEEE Signal Processing Letters, vol. 30, pp. 533-537, 2023, doi: 10.1109/LSP.2023.3270079.
8. Mishra, A., & Pokalwar, S. (2023). JediCode--A Gamefied Approach to Competitive Coding. arXiv preprint arXiv:2311.10244.
9. Kumar, A.P., Nayak, A., K, M.S. et al. A Novel Framework for the Generation of Multiple Choice Question Stems Using Semantic and Machine-Learning Techniques. Int J Artif Intell Educ 34, 332–375 (2024). https://doi.org/10.1007/s40593-023-00333-6 .
10. Lai, PY., Yang, ZR., Dai, QY. et al. BiMuF: a bi-directional recommender system with multi-semantic filter for online recruitment. Knowl Inf Syst 66, 1751–1776 (2024). https://doi.org/10.1007/s10115-023-01997-1.