A fuzzy-XAI framework for customer segmentation and risk detection: integrating RFM, 2-tuple modeling, and strategic scoring
This article presents an interpretable framework for customer segmentation and churn risk detection, integrating fuzzy clustering, explainable AI (XAI), and strategic scoring. The process begins with Fuzzy C-Means (FCM) applied to normalized RFM indicators (Recency, Frequency, Monetary), which were...
| Autor: | |
|---|---|
| Tipo de recurso: | artículo |
| Fecha de publicación: | 2025 |
| País: | España |
| Institución: | Universidad Complutense de Madrid (UCM) |
| Repositorio: | Docta Complutense |
| Idioma: | inglés |
| OAI Identifier: | oai:docta.ucm.es:20.500.14352/129648 |
| Acceso en línea: | https://hdl.handle.net/20.500.14352/129648 |
| Access Level: | acceso abierto |
| Palabra clave: | 658.8 004.8 311 510.6 164 519.226 RFM model fuzzy C-Means clustering 2-tuple linguistic representation analytic hierarchy process (AHP) customer segmentation explainable AI (SHAP, LIME) churn prediction Marketing Inteligencia artificial (Informática) Estadística matemática (Estadística) Lógica simbólica y matemática (Matemáticas) Teoría de la decisión 5311.05 Marketing (Comercialización) 1203.04 Inteligencia Artificial 1209.01 Estadística Analítica 1209.04 Teoría y Proceso de decisión |
| Sumario: | This article presents an interpretable framework for customer segmentation and churn risk detection, integrating fuzzy clustering, explainable AI (XAI), and strategic scoring. The process begins with Fuzzy C-Means (FCM) applied to normalized RFM indicators (Recency, Frequency, Monetary), which were then mapped to a 2-tuple linguistic scale to enhance semantic interpretability. Cluster memberships and centroids were analyzed to identify distinct behavioral patterns. An XGBoost classifier was trained to validate the coherence of the fuzzy segments, while SHAP and LIME provided global and local explanations for the classification decisions. Following segmentation, an AHP-based strategic score was computed for each customer, using weights derived from pairwise comparisons reflecting organizational priorities. These scores were also translated into the 2-tuple domain, reinforcing interpretability. The model then identified customers at risk of disengagement, defined by a combination of low Recency, high Frequency and Monetary values, and a low AHP score. Based on Recency thresholds, customers are classified as Active, Latent, or Probable Churn. A second XGBoost model was applied to predict this risk level, with SHAP used to explain its predictive behavior. Overall, the proposed framework integrated fuzzy logic, semantic representation, and explainable AI to support actionable, transparent, and human-centered customer analytics. |
|---|