Towards Personalized Conversational Sales Agents : Contextual User Profiling for Strategic Action

2025-03-28

AI Summary

Existing conversational recommendation systems (CRSs) struggle to jointly address preference elicitation, recommendation, and persuasive dialogue in e-commerce, where user decisions depend on multifaceted, interdependent factors. Method: We propose “Conversational Sales” (CSales), a novel task formally defined for this setting. We introduce CSUser, a high-fidelity LLM-based user simulator trained on real-world behavioral data, and CSI, a context-aware sales agent capable of dynamic user profiling and personalized strategy planning. Contribution/Results: We establish the first end-to-end, evaluable conversational sales framework covering the full e-commerce decision pipeline. Experiments demonstrate that CSI significantly improves purchase conversion rates and strategic action coherence over multiple dialogue turns, outperforming state-of-the-art CRS baselines. Our work introduces a new paradigm for personalized, goal-oriented sales dialogue agents grounded in realistic user behavior modeling.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Natural Language Processing: Conversational AI/Dialog Systems

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search

Abstract

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 bridge this gap, we introduce Conversational Sales (CSales), a novel task that unifies preference elicitation, recommendation, and persuasion to better support user decision-making. For a realistic evaluation of CSales, we present CSUser, an LLM-based user simulator constructed from real-world data, modeling diverse user profiles with needs and personalities. Additionally, we propose CSI, a conversational sales agent that proactively infers contextual profiles through dialogue for personalized action planning. Extensive experiments demonstrate that CSUser effectively replicates real-world users and emphasize the importance of contextual profiling for strategic action selection, ultimately driving successful purchases in e-commerce.

Problem

• Bridging gap in e-commerce decision-making with personalized recommendations
• Modeling diverse user profiles for realistic conversational sales simulations
• Enhancing strategic action selection via contextual user profiling

Innovation

• LLM-based user simulator for diverse profiles
• Contextual profiling through dialogue for personalization
• Unified task combining recommendation and persuasion