Actionable Interpretability for Churn Classification: A Text Bottleneck Model Case Study at a Major Telecom Provider

Adrian Sauter, Vera Neplenbroek, Georgios Vlassopoulos, Gianluigi Bardelloni

Keywords: Explainable AI, Interpretable NLP, Concept Bottleneck Models, Customer Call Classification, Large Language Models, Telecom Analytics

TL;DR: An interpretable-by-design Text Bottleneck Model combines LLMs with expert-refined concepts to classify customer calls for post-call churn, achieving black-box accuracy while providing transparent, actionable insights for a major telecom provider.

Abstract:

In subscription-based businesses, understanding why a customer intends to churn is as vital as the classification itself. We present a case
study at a large European telecommunications provider, where we implement Text Bottleneck Models (TBMs) for post-call churn classifica-
tion. The TBM distills dialogues into a sparse set of human-interpretable concepts and provides faithful, snippet-based evidence for every
decision. We show that the TBM performs competitively with black-box baselines and demonstrate potential business impact via automated
call profiling and an interactive stakeholder dashboard. Our work demonstrates that the perceived trade-off between interpretability and
predictive performance can be bridged, providing the high-accuracy evidence needed for industrial retention strategies.

Submission Type: Emerging

Submission Number: 235