LLM-Guided Lifecycle-Aware Clustering of Multi-Turn Customer Support Conversations
This addresses the challenge for cloud providers in maintaining scalable, real-time analytics for customer support without disrupting continuity through full reclustering, though it is incremental in nature.
The paper tackles the problem of clustering multi-turn customer support conversations by proposing an adaptive system that segments chats into service-specific concerns and incrementally refines clusters, improving Silhouette Scores by over 100% and reducing Davies-Bouldin Index by 65.6% compared to baselines.
Clustering customer chat data is vital for cloud providers handling multi service queries. Traditional methods struggle with overlapping concerns and create broad, static clusters that degrade over time. Reclustering disrupts continuity, making issue tracking difficult. We propose an adaptive system that segments multi turn chats into service specific concerns and incrementally refines clusters as new issues arise. Cluster quality is tracked via DaviesBouldin Index and Silhouette Scores, with LLM based splitting applied only to degraded clusters. Our method improves Silhouette Scores by over 100\% and reduces DBI by 65.6\% compared to baselines, enabling scalable, real time analytics without full reclustering.