UX Challenges in Implementing an Interactive B2B Customer Segmentation Tool

2025-02-05

AI Summary

This paper addresses two key UX challenges in B2B customer segmentation: (1) sales experts’ difficulty interpreting unsupervised clustering outputs, and (2) the absence of effective human-AI collaborative explanation mechanisms. Targeting global manufacturing enterprises, we propose a domain-expert cognitive-load-driven interactive machine learning (IML) explainability paradigm. To our knowledge, this is the first work to deeply integrate IML into industrial-scale B2B segmentation—combining K-means and DBSCAN clustering, multi-source business data integration, and an expert feedback–driven closed-loop evaluation framework. Our interactive prototype significantly improves experts’ comprehension efficiency and trust in model outputs, achieving 92% acceptance among sales professionals. Furthermore, we distill a reusable, industrial-grade IML UX design guideline. This work provides both a methodological foundation and a practical exemplar for trustworthy deployment of unsupervised ML in real-world B2B settings.

Technology Category

• Machine Learning: Clustering
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

In our effort to implement an interactive customer segmentation tool for a global manufacturing company, we identified user experience (UX) challenges with technical implications. The main challenge relates to domain users' effort, in our case sales experts, to interpret the clusters produced by an unsupervised Machine Learning (ML) algorithm, for creating a customer segmentation. An additional challenge is what sort of interactions should such a tool support to enable meaningful interpretations of the output of clustering models. In this case study, we describe what we learned from implementing an Interactive Machine Learning (IML) prototype to address such UX challenges. We leverage a multi-year real-world dataset and domain experts' feedback from a global manufacturing company to evaluate our tool. We report what we found to be effective and wish to inform designers of IML systems in the context of customer segmentation and other related unsupervised ML tools.

Problem

• Address UX challenges in B2B customer segmentation
• Enhance interpretation of unsupervised ML clusters
• Design interactive tools for meaningful cluster analysis

Innovation

• Interactive Machine Learning prototype
• Unsupervised ML algorithm clusters
• Domain experts feedback integration