Saved in:
Bibliographic Details
Main Authors: Pattnayak, Priyaranjan, Chowdhuri, Sanchari, Agarwal, Amit, Patel, Hitesh Laxmichand
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.04388
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914239634997248
author Pattnayak, Priyaranjan
Chowdhuri, Sanchari
Agarwal, Amit
Patel, Hitesh Laxmichand
author_facet Pattnayak, Priyaranjan
Chowdhuri, Sanchari
Agarwal, Amit
Patel, Hitesh Laxmichand
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_04388
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LLM-Guided Lifecycle-Aware Clustering of Multi-Turn Customer Support Conversations
Pattnayak, Priyaranjan
Chowdhuri, Sanchari
Agarwal, Amit
Patel, Hitesh Laxmichand
Artificial Intelligence
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.
title LLM-Guided Lifecycle-Aware Clustering of Multi-Turn Customer Support Conversations
topic Artificial Intelligence
url https://arxiv.org/abs/2601.04388