SteelLink: AI + Blockchain Enabled B2B Vendor Platform

This paper presented SteelLink, a comprehensive, full-stack AI + Blockchain enabled B2B procurement platform for the Indian steel industry. The system successfully integrates four distinct    technological    layers    —     a     modern Next.js/React frontend, a Node.js/Express/Supabase backend, a Python scikit-learn AI daemon with Streamlit visualisation, and two Ethereum Solidity smart contracts — into a cohesive platform that addresses the industry’s core pain points of vendor fraud, pricing opacity, and procurement inefficiency. The experimental validation confirms that the Supabase database integration is functional ({ error: null, status:  200 }), the Isolation Forest AI engine correctly flags statistical outliers (IF score =−1) for extreme prices like Rs.9,99,999/MT, and the Hardhat-deployed Ethereum smart contracts provide immutable vendor verification anchored primarily to the high-performance Polygon Amoy testnet. By keeping payment processing out of scope and focusing exclusively on the trust and discovery aspects of procurement, SteelLink achieves a clean, legally simple architecture that is nonetheless trans-formative for its target user base. The platform represents a meaningful step toward a more transparent, efficient, and trustworthy steel procurement ecosystem in India.

[1]   World Steel Association, “World Steel in Figures 2023,” Brussels, Belgium, 2023. [Online]. Avail-able: https://worldsteel.org   [2]  S. Nakamoto, “Bitcoin: A Peer-to-Peer Electronic Cash System,” 2008. [Online]. Available: https://bitcoin.org/bitcoin.pdf   [3]   N. Kshetri, “1 Blockchain’s roles in meeting key supply chain management objectives,” Interna-tional Journal of Information Management, vol. 39, pp. 80–89, 2018.   [4]   S. Saberi, M. Kouhizadeh, J. Sarkis, and L. Shen, “Blockchain technology and its relationships to sustainable supply chain management,” International Journal of Production Research, vol. 57, no. 7, pp. 2117–2135, 2019.   [5]  V. Chandola, A. Banerjee, and V. Kumar, “Anomaly detection: A survey,” ACM Computing Surveys (CSUR), vol. 41, no. 3, pp. 1–58, 2009.   [6]   M. Sakurada and T. Yairi, “Anomaly Detection Using Autoencoders with Nonlinear Dimensionality Reduction,” in Proc. MLSDA Workshop, 2021.   [7]  Q. Dai and R. J. Kauffman, “Business Models for Internet-Based B2B Electronic Markets,” Inter-national Journal of Electronic Commerce, vol. 6, no. 4, pp. 41–72, 2002.   [8]    M. Fowler, Patterns of Enterprise Application Architecture. Addison-Wesley, 2003.   [9]    Supabase Inc., “Supabase: The Open Source Firebase Alternative,” 2024. [Online]. Available: https://supabase.com   [10]   Vercel Inc., “Next.js 16 Documentation,” 2024. [Online]. Available: https://nextjs.org/docs