Abstract

Customer prioritization in e-commerce remains dominated by value-based logics that allocate retention effort to the most profitable customers, even though risk-based targeting can be ineffective when intervention responsiveness is ignored. This study aims to develop and empirically test a Value–Risk–Recoverability (VRR) framework that prioritizes service-recovery effort under a fixed intervention budget. The framework draws its three axes from the synergy of three theoretical streams: customer-equity theory motivates the value axis, the churn and defection-management literature motivates calibrated dissatisfaction risk, and service-recovery theory—through the distinction between operational and structural causes of failure—motivates the recoverability axis, which operationalizes the intervention-responsiveness critique of risk-based targeting. The framework is instantiated on the public Brazilian marketplace dataset by Olist (91,954 customers; 93,663 delivered orders, 2016–2018) using unsupervised clustering for behavioral segmentation, calibrated gradient-boosting models to predict order-level dissatisfaction under a strictly temporal hold-out, and SHAP attribution to decompose predicted risk into operational and structural components. Results show that dissatisfaction becomes predictable mainly as fulfillment unfolds (out-of-sample AUC of 0.72 with in-fulfillment signals versus 0.61 at order time); that roughly 76% of predicted risk loads on operational, addressable factors; and that, at a 10% intervention budget, value-based targeting captures only about 30% of realized recoverable value against roughly 96% for risk-aware policies. The study contributes a theoretically grounded, interpretable, and reproducible prioritization logic for service recovery, together with an explicit account of the boundary conditions under which each axis carries decision-relevant information.

IPC Classification

Keywords