CC-OR-Net: A Unified Framework for LTV Prediction through Structural Decoupling

2026-01-15

AI Summary

This study addresses the challenges in customer lifetime value (LTV) prediction arising from zero-inflated and long-tailed data distributions, which often obscure high-value users and mask heterogeneity among low- and mid-value users. To tackle these issues, the authors propose CC-OR-Net, a unified framework that jointly optimizes ranking and regression through architectural decoupling. The model integrates three key components: structured ordinal decomposition, intra-bin residual regression, and targeted enhancement for high-value users, thereby embedding ranking capability directly into its architecture. Evaluated on a real-world dataset of over 300 million users, CC-OR-Net significantly outperforms existing methods, achieving a superior trade-off between overall prediction accuracy and precision in identifying high-value customers, ultimately enhancing business utility.

Technology Category

Machine Learning: Learning Preferences or RankingsComputer Vision: Learning & Optimization for CVSearch and Optimization: Distributed Search

Application Category

User Modeling, Personalization and Recommendation: Fairness-aware retrieval and rankingSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingEconomics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Customer Lifetime Value (LTV) prediction, a central problem in modern marketing, is characterized by a unique zero-inflated and long-tail data distribution. This distribution presents two fundamental challenges: (1) the vast majority of low-to-medium value users numerically overwhelm the small but critically important segment of high-value"whale"users, and (2) significant value heterogeneity exists even within the low-to-medium value user base. Common approaches either rely on rigid statistical assumptions or attempt to decouple ranking and regression using ordered buckets; however, they often enforce ordinality through loss-based constraints rather than inherent architectural design, failing to balance global accuracy with high-value precision. To address this gap, we propose \textbf{C}onditional \textbf{C}ascaded \textbf{O}rdinal-\textbf{R}esidual Networks \textbf{(CC-OR-Net)}, a novel unified framework that achieves a more robust decoupling through \textbf{structural decomposition}, where ranking is architecturally guaranteed. CC-OR-Net integrates three specialized components: a \textit{structural ordinal decomposition module} for robust ranking, an \textit{intra-bucket residual module} for fine-grained regression, and a \textit{targeted high-value augmentation module} for precision on top-tier users. Evaluated on real-world datasets with over 300M users, CC-OR-Net achieves a superior trade-off across all key business metrics, outperforming state-of-the-art methods in creating a holistic and commercially valuable LTV prediction solution.

Problem

• Customer Lifetime Value
• zero-inflated
• long-tail distribution
• value heterogeneity
• high-value users

Innovation

• structural decoupling
• ordinal regression
• residual modeling
• high-value user augmentation
• LTV prediction