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

TL;DR

VALOR introduces a novel framework for B2B revenue uplift modeling that effectively handles high-dimensional treatment signals and aligns with high-value account ranking, leading to significant revenue improvements.

Contribution

The paper proposes VALOR, a unified approach with a Treatment-Gated Sparse-Revenue Network and a new cost-sensitive objective, enhancing uplift modeling accuracy and interpretability in B2B sales.

Findings

20% improvement in rankability over state-of-the-art methods

2.7x increase in incremental revenue per account in production

Validated effectiveness through extensive evaluations and A/B testing

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.