Enhancing Procurement Efficiency through Vendor Relationship Management (VRM) in the FMCG Sector: An Illustrative Research Framework Integrating Natural Language Processing (NLP) and Sentiment Analysis

Abstract

The Fast-Moving Consumer Goods (FMCG) industry operates in a highly competitive environment characterized by short product life cycles, volatile demand, and complex supplier ecosystems. Traditional Vendor Relationship Management (VRM) approaches primarily rely on structured performance metrics such as cost, quality, and delivery performance, often overlooking valuable unstructured information embedded in emails, supplier feedback, meeting transcripts, complaint records, and social media discussions. This conceptual paper proposes an integrated research framework that combines Vendor Relationship Management with Natural Language Processing (NLP) and sentiment analysis to enhance procurement efficiency. The framework suggests that automated analysis of textual interactions can generate actionable insights into supplier trust, collaboration quality, risk signals, and relationship health, thereby improving procurement outcomes. The proposed model contributes to digital procurement literature by positioning AI-enabled text analytics as a strategic capability for procurement decision-making in the FMCG sector.