LLM-Guided Lifecycle-Aware Clustering of Multi-Turn Customer Support Conversations

TL;DR

This paper introduces an adaptive, lifecycle-aware clustering system for multi-turn customer support chats that incrementally refines clusters, significantly improving quality metrics and enabling scalable real-time analytics.

Contribution

It presents a novel approach combining LLM-guided splitting and lifecycle-aware clustering to address issues of static and overlapping clusters in customer chat data.

Findings

Silhouette Scores improved by over 100%

Davies-Bouldin Index reduced by 65.6%

Enables scalable, real-time analytics without full reclustering

Abstract

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.