Saved in:
Bibliographic Details
Main Authors: Guduguntla, Vamshi, Soni, Kavin, Das, Debanshu
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.02472
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914441895870464
author Guduguntla, Vamshi
Soni, Kavin
Das, Debanshu
author_facet Guduguntla, Vamshi
Soni, Kavin
Das, Debanshu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_02472
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle VALOR: Value-Aware Revenue Uplift Modeling with Treatment-Gated Representation for B2B Sales
Guduguntla, Vamshi
Soni, Kavin
Das, Debanshu
Machine Learning
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.
title VALOR: Value-Aware Revenue Uplift Modeling with Treatment-Gated Representation for B2B Sales
topic Machine Learning
url https://arxiv.org/abs/2604.02472