Himanshu Singh, Ashish Yadav, Rizul Singh, Johnson Chaurasiya, Mr. Mudit Dubey
Abstract
Academic qualifications and previous work experience tend to override practical skills in traditional recruitment practices within the contemporary employment ecosystem. This poses a critical obstacle for new graduates and self-taught people with strong technical skills but who are not formally trained for the job. In this research paper, the author introduces RozgaarSetu. This skill-based job application portal aims to change how the recruitment process is conducted by basing it on practical skills and competencies.RozgaarSetu allows users to build comprehensive digital profiles that include their technical experience, certifications, projects, and educational history. The system applies a similar approach to match user profiles to predetermined job specifications and showcase opportunities. Where the user fails to meet eligibility requirements, the platform offers a skill gap analysis and improvement recommendations.The paper will discuss the purpose, process, use, advantages, and the future of RozgaarSetu. The results show that skill-based recruitment platforms will have a considerable positive impact on employment opportunities, increasing hiring efficiency and helping close the gap between industry needs and students’ abilities.
RozgaarSetu is a new way out of the problems that were encountered in old recruitment systems. By prioritising skills over academic backgrounds, it creates a just and effective job market for job seekers and recruiters.The system makes hiring easy, enhances candidate selection, and helps bridge the gap between industry requirements and education. It empowers fresh graduates and promotes a culture of lifelong learning and competence.
The platform is highly applicable to the real world and can play a major role in improving employment rates and the quality of the workforce.
References
[1] Albrecht, J., & Chen, Y. (2023). Enhancing Job Matching Algorithms: A Review of Current Practices in Online Job Portals. International Journal of Human-Computer Studies, 150, 102–115.
[2] Bhatia, & Kapoor. examined the integration of machine learning and NLP techniques in job portal applications, highlighting their potential to optimize job matching.
[3] Devlin et al. introduced BERT, a deep bidirectional transformer model, demonstrating its efficacy in understanding natural language through pre-training on large text corpora.
[4] Gupta, S., & Raj, S. (2021). Enhancing Resume Screening with Deep Learning Models. International Journal of Artificial Intelligence Research, 7, 202–211.
[5] Khan, M. S., & Khan, M. S. (2015). Online Job Portal. (Doctoral dissertation, University of Management and Technology Lahore).
[6] Kummer, J., Bär, H., & Sieben, M. (2020). Improving Resume Matching for Job Portals Using Natural Language Processing. Proceedings of the International Conference on Computational Linguistics, 1342–1351.
[7] Kumar, S., & Gupta, R. (2021). The Role of Technology in Recruitment: A Comprehensive Review of Job Portal Innovations. Journal of Business Research, 134, 123–130.
[8] Le, Q. V., Mikolov, T., & Reimers, M. (2013). Word2Vec: Distributed Representations of Words and Phrases and Their Compositionality. Proceedings of NeurIPS, 2477–2485.
[9] Lee, H., & Park, S. (2022). Mobile Accessibility in Job Portals: An Analysis of User Experience and Engagement. Journal of Information Technology, 37(2), 145–160.
[10] Liu et al. introduced RoBERTa, an optimized version of the BERT pretraining model, improving performance through better training strategies.
[11] Mithun, G. (2020). A Project Report on Job Portal. (Doctoral dissertation, CMR Institute of Technology, Bangalore).
[12] Patel, A., & Sharma, R. (2020). Security Challenges in Online Job Portals: A Case Study on User Data Protection. Journal of Cybersecurity, 5(1), 1–10.
[13] Pinjari, M., De, N., Kokne, R., Siddiqui, A., & Chitre, D. (2019). Online Job Portal. International Research Journal of Engineering and Technology.
[14] Raghavendra, H., & Shankar, P. (2023). Integrating AI in Job Portals: Trends and Future Directions. Journal of Management Information Systems, 40(3), 90–110.
[15] Singh, V., & Yadav, R. (2021). User-Centric Design Approaches for Job Portals: A Study on Enhancing User Experience. International Journal of Design, 15(2), 11–20.
[16] Sun et al. presented methods for fine-tuning BERT for text classification tasks across different datasets.
[17] Vaswani et al. introduced the Transformer architecture, relying entirely on attention mechanisms for NLP tasks.
[18] Zhang and Zhao explored the use of AI technologies in recruitment platforms, focusing on resume parsing and job portal systems.
[19] Zhang, Wei, and Zhang applied deep learning and NLP models to improve job portal efficiency and AI-based recruitment.
[20] Zhao, L., & Chen, X. (2022). The Impact of Social Media Integration on Job Portal Effectiveness: A Quantitative Analysis. Journal of Marketing Research, 59(4), 341–355
How to Cite This Paper
Himanshu Singh, Ashish Yadav, Rizul Singh, Johnson Chaurasiya, Mr. Mudit Dubey (2026). RozgaarSetu- Skill Based Job Application Portal. International Journal of Computer Techniques, 13(2). ISSN: 2394-2231.
