Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM67572
Volume:
10 |
9 |
Sep 2026
Pages:
1-7
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.

Department of Computer Science & Engineering
P. R. Pote Patil College of Engineering & Management, Amravati

Department of Computer Science & Engineering
P. R. Pote Patil College of Engineering & Management, Amravati

Department of Computer Science & Engineering
P. R. Pote Patil College of Engineering & Management, Amravati

Department of Computer Science & Engineering
P. R. Pote Patil College of Engineering & Management, Amravati

Department of Computer Science & Engineering
P. R. Pote Patil College of Engineering & Management, Amravati

Department of Computer Science & Engineering
P. R. Pote College of Engineering & Management, Amravati
Professional networking is a big part of how entrepreneurs, investors, mentors, and business leaders actually end up finding the right opportunities and the right people. But as organizations grow, going through thousands of member profiles by hand stops being practical, and a lot of good connections simply get missed. This paper presents an AI-Powered Member Matchmaking Agent built for TiE (The Indus Entrepreneurs), a global non-profit that supports entrepreneurship and innovation, to deal with exactly this problem. The system lets a member type their requirement in plain English — the kind of entrepreneur, industry, location, company size, or business interest they are looking for — and the backend takes it from there. It processes member profile information using TF-IDF based keyword matching along with sentiment analysis, and returns the most relevant matches ranked by profile similarity and business context. The system is built to keep working as the member database keeps growing, the system doesn't need any major changes to keep up with it. Down the line, it can also pull in things like company websites, news pieces, and other publicly available business info to fill in the gaps in existing profiles. Member privacy isn't an afterthought here either — confidential data stays locked down the whole time, even as the matching itself keeps getting sharper. Overall, the proposed solution cuts down manual effort and makes matches more accurate, which should help TiE members network and collaborate a lot more effectively.
KEYWORDS
The AI-Powered Member Matchmaking Agent addresses a real, practical problem inside professional networking organizations like TiE — finding the right connection inside a large and growing member base without relying on manual searching. By combining NLP-based query understanding with TF-IDF matching and sentiment analysis, the system turns plain English queries into ranked, relevant member recommendations. It is designed to work with a growing dataset and to improve further as profiles are enriched with external business information, all while keeping member data secure and private. Overall, the system is meant to reduce manual networking effort, improve the relevance of connections made, and support stronger collaboration within the TiE community. Future work can build on this foundation by adding semantic matching and richer data enrichment to push recommendation quality even further.
[1] Q. Zhang, J. Lu, and Y. Jin, "Artificial Intelligence in Recommender Systems," Complex & Intelligent Systems, Springer, Heidelberg, vol. 7, no. 1, 2021, pp. 439–457. [2] Z. Wang, J. Liao, Q. Cao, H. Qi, and Z. Wang, "Friendbook: A Semantic-Based Friend Recommendation System for Social Networks," IEEE Transactions on Mobile Computing, IEEE, vol. 14, no. 3, 2015, pp. 538–551. [3] N. Reimers and I. Gurevych, "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks," Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Association for Computational Linguistics, Hong Kong, China, 2019, pp. 3982–3992. [4] S. Tuarob, N. Assavakamhaenghan, W. Tanaphantaruk, P. Suwanworaboon, S. U. Hassan, and M. Choetkiertikul, "Automatic Team Recommendation for Collaborative Software Development," Empirical Software Engineering, Springer, vol. 26, no. 4, 2021, pp. 1–53. [5] E. Masciari, A. Umair, and M. H. Ullah, "A Systematic Literature Review on AI-Based Recommendation Systems and Their Ethical Considerations," IEEE Access, IEEE, vol. 12, 2024, pp. 121223–121241. [6] G. Poveda, A. Westerski, and C. A. Iglesias, "Application of Semantic Search in Idea Management Systems," International Conference for Internet Technology and Secured Transactions, IEEE Xplore, 2012, pp. 230–236.
Publication Date
10/3/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
4
Total views since publication
PDF Downloads
9
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...