Advanced Algorithms and Implementations for Talent Matching and Team Formation in Crowdsourced Engineering

1.      ConclusionThis project successfully developed and implemented TalentBridge, an automated platform that efficiently optimizes hackathon team matching and skill extraction. By leveraging a Hybrid Machine Learning synergy based on data-driven insights(ML) pipeline (KeyBERT for NLP and K-Means Clustering) and real-time APIs, the system directly achieves its core aims and objectives. The system streamlines the complex team formation process, making it scalable and user-friendly, and enhances overall participation. The technologies clearly demonstrate the potential for improved match quality and higher success rates for hackathon projects compared to conventional static methods.

[1]     Yasir Munir et al., "Developer Recommendation and Team Formation in Collaborative Crowdsourcing Platforms," IEEE Access, vol. 2025, pp. xx-xx, 2025. DOI: 10.1109ACCESS.2025.3558557   [2]     Aymen Hamrouni, Hakim Ghazzai, Turki Alelyani, Yehia Massoud, "Low Complexity Recruitment for Collaborative Mobile Crowdsourcing Using Graph Neural Networks," arXiv, 2021. arXiv2106.00717   [3]     Various authors, "Team Formation in Software Engineering: A Systematic Mapping Study," IEEE Access, 2021.   [4]     Hamrouni A., Ghazzai H., Alelyani T., Massoud Y., "A Stochastic Team Formation Approach for Collaborative Mobile Crowdsourcing," arXiv/IEEE Conf., 2020. arXiv2004.13881   [5]     Xinqiang Xie, Bin Wang, Xiaochun Yang, "SoftRec Multi-Relationship Fused Software Developer Recommendation," MDPI Applied Sciences, 2020.   [6]     Farhadi, Sorkhi, Hashemi, Hamzeh, "An Effective Expert Team Formation in Social Networks Based on Skill Grading," IEEE ICDMW, 2011.   [7]     Liangyue Li, Hanghang Tong, et al., "Enhancing Team Composition in Professional Networks: Problem Definitions and Fast Solutions," IEEE TKDE, 2016.   [8]     Brown et al., "OpenAI Language Models are Few-ShotLearners.