Sarcouncil Journal of Engineering and Computer Sciences

Abstract: Inventory substitution is a crucial aspect of supply chain optimization that ensures business continuity while managing risks associated with material obsolescence, availability issues, and product composition changes. This paper presents a structured approach to substituting old materials with new alternatives based on a set of predefined coefficients. The study categorizes supply factors into internal and external components and discusses mitigation strategies to optimize inventory substitution effectively. Advanced methodologies, including AI-driven demand forecasting and digital supply chain monitoring, are explored to enhance substitution accuracy. This paper presents a quantitative, AI-driven framework for inventory substitution in the cosmetic industry — a sector where material obsolescence, sustainability constraints, and volatile global supply dynamics increasingly challenge operational continuity. The study introduces a coefficient-based substitution model, separating decision parameters into internal and external factors, each evaluated through a multi-criteria decision-making (MCDM) lens. A Random Forest Classification algorithm is applied to predict optimal material replacements, using attributes such as cost, supplier reliability, eco-friendliness, lead time, and regulatory compliance. Mathematical modeling formalizes the weighting of substitution coefficients, ensuring balanced decision outcomes. Empirical simulation demonstrates measurable benefits: a 25% reduction in material obsolescence, 18% cost savings, and improved regulatory adherence. The research integrates AI, supply chain analytics, and sustainability frameworks, demonstrating how material substitution can evolve from a reactive practice into a strategic optimization discipline. The proposed model sets the foundation for digital, data-driven procurement practices adaptable across industries.