VALOR: Value-Aware Revenue Uplift Modeling with Treatment-Gated Representation for B2B Sales

arXiv cs.LG / 4/6/2026

📰 NewsSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper introduces VALOR, a value-aware B2B revenue uplift modeling framework designed to identify “persuadable” accounts from zero-inflated revenue distributions for more efficient human sales targeting.
It addresses common uplift modeling failures—such as treatment signal collapse in high-dimensional settings and mismatch between calibration and ranking of high-value accounts (“whales”).
VALOR uses a Treatment-Gated Sparse-Revenue Network with bilinear interactions and optimizes with a cost-sensitive focal objective plus a value-weighted ranking loss tied to financial magnitude.
For interpretability in high-touch sales motions, the authors derive Robust ZILN-GBDT, a tree-based variant focused on uplift heterogeneity via a custom splitting criterion.
Experiments show strong results, including a 20% improvement in rankability versus state-of-the-art methods on public benchmarks and a 2.7x increase in incremental revenue per account in a 4-month production A/B test.

Abstract

B2B sales organizations must identify "persuadable" accounts within zero-inflated revenue distributions to optimize expensive human resource allocation. Standard uplift frameworks struggle with treatment signal collapse in high-dimensional spaces and a misalignment between regression calibration and the ranking of high-value "whales." We introduce VALOR (Value Aware Learning of Optimized (B2B) Revenue), a unified framework featuring a Treatment-Gated Sparse-Revenue Network that uses bilinear interaction to prevent causal signal collapse. The framework is optimized via a novel Cost-Sensitive Focal-ZILN objective that combines a focal mechanism for distributional robustness with a value-weighted ranking loss that scales penalties based on financial magnitude. To provide interpretability for high-touch sales programs, we further derive Robust ZILN-GBDT, a tree based variant utilizing a custom splitting criterion for uplift heterogeneity. Extensive evaluations confirm VALOR's dominance, achieving a 20% improvement in rankability over state-of-the-art methods on public benchmarks and delivering a validated 2.7x increase in incremental revenue per account in a rigorous 4-month production A/B test.