dorsal/arxiv
View SchemaCC-OR-Net: A Unified Framework for LTV Prediction through Structural Decoupling
| Authors | Mingyu Zhao, Haoran Bai, Yu Tian, Bing Zhu, Hengliang Luo |
|---|---|
| Categories | |
| ArXiv ID | 2601.10176vv2 |
| URL | https://arxiv.org/abs/2601.10176 |
| License | http://creativecommons.org/licenses/by/4.0/ |
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.
{
"annotation_id": "094d4113-92df-4784-b7b1-52b360afd6da",
"date_created": "2026-02-17T05:53:24.341000Z",
"date_modified": "2026-02-17T05:53:24.341000Z",
"file_hash": "46f8c1382c28e8bcd90ad4b5da4e7512bc5ae4614cf0766a3df90b24654f1d29",
"private": false,
"record": {
"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.",
"arxiv_id": "2601.10176",
"authors": [
"Mingyu Zhao",
"Haoran Bai",
"Yu Tian",
"Bing Zhu",
"Hengliang Luo"
],
"categories": [
"cs.LG"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"title": "CC-OR-Net: A Unified Framework for LTV Prediction through Structural Decoupling",
"url": "https://arxiv.org/abs/2601.10176",
"version": "v2"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "0685a5c7-fafc-4d8a-a8cd-31b92e982268",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}