Optimizing Supplier Selection and Inventory Management through Artificial Intelligence for Sustainable Purchasing in SMEs

Project Abstract

This study presents a comprehensive framework for optimizing supplier selection and inventory management in small and medium-sized enterprises (SMEs) using artificial intelligence (AI) to enhance sustainability in purchasing practices. The research addresses the pressing need for cost efficiency, supply resilience, and environmental responsibility within resource-constrained SME contexts by integrating data-driven decision-making with procurement operations. A mixed-methods approach is adopted, combining quantitative modeling, machine learning, and qualitative insights from industry stakeholders to develop and validate an AI-enabled decision-support system (DSS) for procurement. The core objective is to minimize total cost of ownership (TCO) while maximizing supplier performance, risk mitigation, and environmental impact reduction across procurement, warehousing, and logistics activities. The study begins with a thorough literature synthesis to identify gaps in supplier selection methodologies, inventory optimization under demand volatility, and the application of AI techniques in sustainable purchasing. Based on these insights, a multi-objective optimization model is developed that simultaneously optimizes supplier qualification, contract terms, order quantities, reorder points, safety stock, and transportation modes under uncertainties such as demand fluctuations, supplier lead times, and carbon footprint constraints. Advanced AI methods, including predictive analytics for demand forecasting, supplier risk scoring, and reinforcement learning for dynamic procurement scheduling, are integrated into the model to enable adaptive decision-making. The DSS leverages historical procurement data, supplier performance metrics, and sustainability indicators to generate interpretable recommendations and actionable scenarios for procurement managers. Empirical validation is conducted through a case study in a representative SME sector, with data on supplier catalogs, pricing, delivery reliability, quality metrics, and sustainability attributes. Simulation experiments compare the AI-driven approach against traditional purchasing strategies, evaluating performance across multiple KPIs total cost reduction, service level, inventory turnover, stockouts, supplier diversity, and environmental metrics such as CO2 emissions and waste minimization. Sensitivity analyses assess the robustness of the model to variations in demand patterns, supplier behavior, and policy constraints. The results demonstrate that AI-enhanced supplier selection and inventory management can achieve significant improvements in cost efficiency and sustainability performance, including a measurable reduction in stockouts and a more resilient supply base with improved supplier collaboration. A key contribution is the development of a scalable, SME-oriented DSS architecture that enables practitioners to implement AI-infused purchasing practices with limited data, computational resources, and organizational change requirements. The research also provides guidelines for data governance, model interpretability, and stakeholder management to facilitate adoption. Limitations include potential data quality issues, model transferability across industries, and the need for ongoing calibration to reflect evolving supplier ecosystems. The study concludes with actionable recommendations for managers and policymakers seeking to embed AI-enabled sustainability into SME purchasing strategies, along with avenues for future research in cross-sector procurement optimization and the integration of circular economy principles.

Project Overview

What This Project Is About

---

A straightforward, non-technical overview of choosing suppliers and managing inventory with the help of AI ideas to make purchasing in small and medium-sized enterprises (SMEs) more sustainable.

---

---

The Problem It Addresses

---

Small businesses often struggle with choosing reliable suppliers and keeping inventory costs under control. Delays, poor quality, or overstock can harm cash flow and customer satisfaction. The project looks at how simple AI ideas can help with better supplier choices and smarter stock management.

---

---

Objectives of the Project

---

1. Explain what supplier selection and inventory management mean in plain language.
2. Identify common challenges faced by SMEs in purchasing and stocking goods.
3. Show how basic AI tools can support better supplier decisions and stock levels.
4. Suggest practical steps SMEs can use to implement these ideas cost-effectively.

---

---

What You Will Do Step by Step

---

1. Review existing literature to understand current practices in supplier selection and inventory management.
2. Collect simple data from a local SME (e.g., supplier names, delivery times, prices, stock levels).
3. Describe how AI concepts could help, without heavy technical detail.
4. Propose a small, practical framework or checklist for SMEs to apply.
5. Discuss potential benefits and limitations of using AI in procurement and stock control.

---

---

Expected Outcome

A clear, easy-to-use framework or set of guidelines for SMEs to improve supplier selection and inventory management through AI-assisted ideas, along with anticipated benefits like lower costs, fewer stockouts, and better supplier reliability.