Retailer segmentation is the strategic process for retail firms as it optimizes channel management, thus significantly enhances the business performance. Retailer Segmentation based on diverse criteria such as operational efficiency, financial stability, and technological adoption enable retail firms to adopt custom engagement strategies, allocate resources effectively, and mitigate risks. Besides, organizing diverse criteria into broader dimensions reduces inherent complexity in strategizing the retailer segmentation decisions. Moreover, the use of combination of quantitative and qualitative criteria provides good contextual understanding of a retailer’s characteristics, thereby minimizing the bias in decisions. Industry 4.0 is revolutionizing complex strategic processes such as retailer segmentation using artificial intelligence (AI) through data-driven, automated, and predictive capabilities. However, existing AI models often lack contextual relevance and interpretability, thereby limiting their applicability in complex retailer segmentation tasks. This study intends to address these limitations by conceptualizing an intelligent method based on Explainable AI (XAI), utilizing knowledge graph. Empirical data is collected and used in this study to conceptualize the retailer segmentation method. This method uncovers the hidden knowledge in the data about a retailer’s performance using Knowledge Graph model and infers appropriate segmentation category for a retailer. Further, this method adopts a reasoning technique to generate interpretable explanations for inferences. This study helps practitioners better understand how to use Knowledge Graph models for retailer segmentation, which can be extended and scaled in future research.
Shiralkar et al. (Thu,) studied this question.