THE ROLE OF ARTIFICIAL INTELLIGENCE IN VENDOR PERFORMANCE EVALUATION WITHIN DIGITAL RETAIL SUPPLY CHAINS: A REVIEW OF STRATEGIC DECISION-MAKING MODELS

Abstract

The digital transformation of retail supply chains has fundamentally reshaped how organizations evaluate, manage, and engage with their suppliers. In this context, artificial intelligence (AI) has emerged as a transformative enabler, offering sophisticated tools for enhancing vendor performance evaluation through intelligent automation, predictive modeling, and real-time decision-making support. This systematic review critically examines the integration of AI technologies—such as supervised and unsupervised machine learning, natural language processing (NLP), and deep learning algorithms—into vendor performance assessment frameworks within digital retail ecosystems. Drawing on an analysis of 86 peer-reviewed journal articles, industry white papers, and technical reports published between 2015 and 2022, the study identifies and categorizes the predominant AI-driven models employed to assess key supplier attributes, including reliability, quality assurance, compliance with contractual obligations, cost-efficiency, and operational risk. The review further investigates how these AI tools enable real-time vendor monitoring, dynamic anomaly detection, and the automation of adaptive performance scorecards. Evidence from the literature demonstrates that AI-enabled evaluation systems can significantly enhance the precision, objectivity, and scalability of vendor assessments, while reducing human bias and manual inefficiencies in procurement processes. However, the adoption of AI in this domain is not without challenges. Common barriers include fragmented data architectures, difficulties in integrating AI tools with legacy enterprise systems, concerns over the interpretability and ethical transparency of algorithmic decisions, and a lack of standardization in AI governance practices. In response to these challenges, the review also identifies emergent research opportunities aimed at improving the accountability, fairness, and sustainability of AI applications in retail supply chains. Future research directions include the development of hybrid models combining human expertise with machine learning, reinforcement learning-based adaptive evaluation systems, and the incorporation of ESG (environmental, social, and governance) metrics into AI-based vendor assessments. This review contributes to the growing discourse on AI’s role in shaping agile, data-driven, and ethically sound vendor management practices within the evolving digital retail ecosystem. By synthesizing current findings, the review highlights critical implementation bottlenecks and knowledge gaps in the field, and proposes future research directions for developing explainable, secure, and ethically sound AI solutions that align with sustainable procurement goals and evolving retail strategies.