محمدرضا کوششی

Understanding and managing customer engagement are crucial in co-creating value and sustaining long-term customer relationships. This study develops a predictive segmentation model tailored to the banking sector, with a specific focus on emerging market contexts. Employing a mixed-methods approach, the research integrates a meta-synthesis of prior studies with a C5.0 decision tree algorithm to identify key engagement drivers. The novelty of the study lies in its integration of Relational Models Theory, Customer Lifecycle stages, and perceived emotional value into a unified predictive framework. A structured survey was administered to Iranian retail banking customers and the model segmented them based on their emotional and functional value perceptions, relational orientations, and lifecycle stages. Findings revealed that emotional value is the most influential predictor of engagement, followed by relationship stage and relational model type. Four distinct customer segments were identified, each with unique engagement profiles. The study offers practical tools for banks to personalize CRM strategies and optimize engagement efforts based on relational and behavioral insights. This research contributes to the literature by combining the relational theory and behavioral prediction within a service-dominant logic, offering actionable insights for banking institutions operating in culturally specific, emerging markets.