Optimizing Supplier Selection and Contract Management Using Artificial Intelligence for Sustainable Procurement in Manufacturing Firms

Project Abstract

This study develops an integrated framework that leverages artificial intelligence to optimize supplier selection and contract management within sustainable procurement for manufacturing firms. The research addresses pressing challenges in procurement supplier risk, total cost of ownership, compliance with ESG standards, dynamic market conditions, and contract performance variability. A mixed-methods approach combines a quantitative optimization model, machine learning-based supplier risk scoring, and natural language processing for contract analytics to deliver actionable decision-support tools for procurement professionals. The core model blends a multi-objective supplier selection algorithm with contract optimization that explicitly accounts for sustainability criteria, supplier capacity, lead times, and quality performance. The AI-enabled decision support system (DSS) uses supervised learning to predict supplier reliabilities and potential disruptions, unsupervised clustering to segment suppliers by capability and sustainability profiles, and reinforcement learning to adapt procurement strategies over time under changing demand scenarios. The contract management component employs natural language processing to extract key terms, monitor compliance, and detect anomalies in real-time, while a contract risk index quantifies exposure to price volatility, regulatory shifts, and supplier bankruptcies. Together, these components enable simultaneous optimization of supplier mix, contract terms, and risk-adjusted performance metrics, yielding improvements in cost efficiency, supply resilience, and environmental impact. A case study in a mid-to-large scale manufacturing firm demonstrates the framework's practical viability. Data from supplier performance records, procurement transactions, contract documents, and sustainability reports feed the models, with preprocessing to address data quality and confidentiality. The results indicate statistically significant improvements in total procurement cost (reduction of 8–15%), on-time delivery (increase of 12–20%), and defect rates (down 6–11%), alongside measurable gains in environmental performance such as reduced carbon footprint and higher share of sustainable suppliers. Sensitivity analyses reveal the robustness of the framework to data uncertainty, market shocks, and shifting regulatory requirements. The study also analyzes the trade-offs between cost minimization and sustainability goals, providing decision-makers with scenario-based recommendations and risk dashboards. Key contributions include (1) a novel AI-driven, multi-criteria optimization model for supplier selection that integrates ESG dimensions; (2) an automated contract analytics and monitoring module that enhances compliance and performance visibility; (3) a dynamic, learning-based procurement strategy that adapts to market and demand changes; and (4) a validated, scalable architecture suitable for deployment in diverse manufacturing contexts. The framework advances sustainable procurement by marrying advanced analytics with practical procurement governance, offering a decision-support toolkit that reduces operational risk while promoting responsible sourcing and long-term competitive advantage.

Project Overview

What This Project Is About

---

A straightforward exploration of how buyers select suppliers and manage contracts using simple, beginner-friendly ideas and basic AI concepts to support sustainable procurement in manufacturing.

---

---

The Problem It Addresses

---

Many manufacturing firms struggle with choosing reliable suppliers, negotiating favorable terms, and ensuring long-term sustainability. The project looks at gaps in transparency, risk, and alignment with environmental and social goals.

---

---

Objectives of the Project

---

1. Describe current supplier selection and contract practices in simple terms.
2. Explain how basic AI tools can help compare suppliers on cost, quality, and sustainability.
3. Propose a practical, step-by-step framework for sustainable procurement decisions.
4. Demonstrate how a simple model could flag risks and suggest contract improvements.

---

---

What You Will Do Step by Step

---

1) Review introductory material on procurement and sustainability. 2) Gather sample supplier data or use publicly available datasets. 3) Learn simple evaluation criteria (cost, lead time, quality, compliance, carbon footprint). 4) Build a basic decision aid, using straightforward AI ideas like scoring and rule checks. 5) Test the tool with a pretend procurement scenario. 6) Discuss how results support better supplier choices and contracts. 7) Reflect on limitations and ethical considerations.

---

---

Expected Outcome

A simple, usable framework and a small decision aid that helps students or practitioners evaluate suppliers and contracts with sustainability in mind, plus an overview of benefits and potential risks.