Einstein International Journal Organization(EIJO)

Abstract 

This paper presents Smart Connect, an AI-powered professional networking and career development platform designed to bridge the gap between job seekers and employers through intelligent, data-driven matching. Conventional job search platforms rely predominantly on keyword-based filtering, which fails to capture the contextual and semantic nuances of candidate profiles and job requirements, resulting in suboptimal matches. SmartConnect addresses these limitations by integrating machine learning (ML), natural language processing (NLP), and Large Language Models (LLMs) to perform deep semantic analysis of resumes and job descriptions. The system employs a hybrid recommendation engine combining content-based filtering, collaborative filtering, and transformer-based contextual embeddings (BERT, RoBERTa) to generate accurate, personalized, and explainable job recommendations. Additionally, the platform incorporates explainable AI (XAI) techniques to ensure transparency in recommendation decisions, fostering user trust and engagement. Experimental evaluation demonstrates significant improvements in precision, recall, Normalized Discounted Cumulative Gain (NDCG), and Mean Reciprocal Rank (MRR) over baseline approaches. The proposed system represents a meaningful advancement toward smarter, fairer, and more user-centric professional networking in the modern digital employment landscape.

1. S. Rojas-Galeano, J. Posada, and E. Ordoñez, “A Bibliometric Perspective on AI Research for Job-Résumé Matching,” The Scientific World Journal, vol. 2022, p. 8002363, 2022.
2. M. J. Wilson et al., “Navigating the Career Transition from Industry to Academia,” Industry and Higher Education, vol. 28, no. 1, pp. 5–13, Feb. 2014.
3. L. Sivabalan, R. Yazdanifard, and N. H. Ismail, “How to Transform the Traditional Way of Recruitment into Online System,” International Business Research, vol. 7, 2014. https://doi.org/10.5539/ibr.v7n3p178.
4. “Artificial Intelligence and Labour Market Matching,” OECD Social, Employment and Migration Working Papers, Jan. 2023. https://doi.org/10.1787/2b440821-en.
5. R. Thali et al., “Survey on Job Recommendation Systems Using Machine Learning,” in Proc. ICIDCA, Mar. 2023, pp. 453–457.
6. N. Supriyono et al., “Advancements in Natural Language Processing: Implications, Challenges, and Future Directions,” Telematics and Informatics Reports, Elsevier BV, Nov. 2024, pp. 100173.
7. Z. Zheng et al., “Generative Job Recommendations with Large Language Model,” ArXiv, July 2023. https://doi.org/10.48550/arXiv.2307.02157.
8. G. Preetam and V. Sadaphal, “JobRecoGPT — Explainable Job Recommendations Using LLMs,” ArXiv, Sept. 2023. https://doi.org/10.48550/arxiv.2309.11805.
9. F. Abel et al., “RecSys Challenge 2016: Job Recommendations,” in Proc. 10th ACM RecSys, pp. 425–426, 2016.
10. F. Abel et al., “RecSys Challenge 2017: Offline and Online Evaluation,” in Proc. 11th ACM RecSys, pp. 372–373, 2017.
11. C. C. Aggarwal, Recommender Systems. Springer, 2016.
12. S. Ahmed et al., “User Interaction Analysis to Recommend Suitable Jobs in Career-Oriented Social Networking Sites,” in Proc. ICoDSE, pp. 1–6, IEEE, 2016.
13. S. T. Al-Otaibi and M. Ykhlef, “A Survey of Job Recommender Systems,” Int. J. Physical Sciences, vol. 7, no. 29, pp. 5127–5142, 2012.
14. N. D. Almalis, G. A. Tsihrintzis, and E. Kyritsis, “A Constraint-Based Job Recommender System Integrating FoDRA,” Int. J. Computational Intelligence Studies, vol. 7, no. 2, pp. 103–123, 2018.
15. D. Arya, V. Ha-Thuc, and S. Sinha, “Personalized Federated Search at LinkedIn,” in Proc. 24th ACM CIKM, pp. 1699–1702, 2015.
16. J. Bandy, “Problematic Machine Behavior: A Systematic Literature Review of Algorithm Audits,” Proc. ACM Human-Computer Interaction, vol. 5, no. CSCW1, pp. 1–34, 2021.
17. S. Bansal, A. Srivastava, and A. Arora, “Topic Modeling Driven Content Based Jobs Recommendation Engine for Recruitment Industry,” Procedia Computer Science, vol. 122, pp. 865–872, 2017.
18. M. Bastian et al., “LinkedIn Skills: Large-Scale Topic Extraction and Inference,” in Proc. 8th ACM RecSys, pp. 1–8, 2014.