Towards Personalized Conversational Sales Agents: Contextual User Profiling for Strategic Action
This addresses the need for more realistic conversational recommender systems in e-commerce, though it appears incremental as it builds on existing CRS frameworks.
The paper tackles the problem of creating conversational sales agents that can handle complex e-commerce decision-making by introducing the CSALES task, which integrates preference elicitation, recommendation, and persuasion. The proposed CSI agent significantly improves recommendation success and persuasive effectiveness across diverse user profiles.
Conversational Recommender Systems (CRSs)aim to engage users in dialogue to provide tailored recommendations. While traditional CRSs focus on eliciting preferences and retrieving items, real-world e-commerce interactions involve more complex decision-making, where users consider multiple factors beyond simple attributes. To capture this complexity, we introduce Conversational Sales (CSALES), a novel task that integrates preference elicitation, recommendation, and persuasion within a unified conversational framework. To support realistic and systematic evaluation, we present CSUSER, an evaluation protocol with LLM-based user simulator grounded in real-world behavioral data by modeling fine-grained user profiles for personalized interaction. We also propose CSI, a conversational sales agent that proactively infers contextual user profiles and strategically selects actions through conversation. Comprehensive experiments show that CSI significantly improves both recommendation success and persuasive effectiveness across diverse user profiles.