AHFE Open AccessAutomating customer feedback in online marketplaces with retrieval augmented generation
Abstract
This paper proposes a solution for automating customer review responses in online marketplaces. The goal is to save time and resources for sellers. The proposed system combines traditional methods with Large Language Models, allowing the sellers to provide a personalized service and improve customer satisfaction. The system has been implemented and integrated with two main online marketplaces in Russia: Wildberries and Ozon. The study demonstrates promising results in terms of response quality and efficiency. In particular, the system was used to answer more than 3800 reviews for three sellers, which was estimated to be an equivalent of 120 working hours.
Keywords: Automation, LLM, RAG, E-commerce, Customer Support, Customer Service
DOI: 10.54941/ahfe1005849
Cite this paper
More from this volume
- Concept and development of a user interface for human-robot collaboration during a safety briefing
- User-centered design of professional social service robots
- Human Systems Integration and Design in Port Terminal Concessions: A Bibliometric Study of End – of – Life Management and Decommissioning Guidelines
- State-of-the-art in human-centric studies of AI-enhanced situational awareness within the security domain
- Humans and AI writing lectures together
- Digital Networking for Economic Growth: Interactions Between Natural and Artificial Intelligence
- Dynamic Alarm Information Presentation Strategy under the Influence of Dynamic Elements in Smart Factory.
- Development of Techniques for Measuring Lower Limb Flexibility in the Elderly
- Real-Time Cognitive Tools for Space Systems
- Analysis of experimental consensus-building tasks with evaluation indices
- An Action Recognition Method based on 3D Feature Fusion
- The effect of Hue difference in vibration environment on the cognitive performance of aircraft HUD Interface for pilots