Examining the Effect of AI-Powered Virtual Human Live Streaming on Consumer Repurchase Intention

AI-powered virtual humans are increasingly used as live streaming presenters, yet it remains unclear how consumers translate experiences with these embodied agents into trust and repurchase intention. Rather than tracing a complete multi-stage consumer journey, this study focuses on a recent virtual human live streaming session as a focal touchpoint that compresses product discovery, evaluation, interaction, and purchase support. Integrating consumer touchpoint logic with the Stimulus–Organism–Response (S-O-R) framework, we examine how perceptual touchpoint experience (active control, synchronicity, and two-way communication) and cognitive touchpoint experience (perceived expertise and perceived competence) shape consumer trust and repurchase intention. Using survey data from 305 consumers with virtual human live streaming experience, this study tested the proposed model via partial least squares structural equation modeling (PLS-SEM) and supplemented the findings with fuzzy-set qualitative comparative analysis (fsQCA). The results showed that both perceptual and cognitive touchpoint experiences significantly enhanced trust, which partially mediated their effects on repurchase intention; cognitive touchpoint experience also exerted a strong direct effect on repurchase intention. The fsQCA results revealed two equifinal configurations leading to high repurchase intention: a full-experience path (high perceptual experience + high cognitive experience + high trust) and a capability-dominant path (low perceptual experience + high cognitive experience + high trust). This study contributes to virtual human commerce research by distinguishing interaction-process cues from competence-based source cues and by showing when AI-powered live streaming can support post-touchpoint retention.