CanniUplift: A Holistic Framework for Mitigating Seller and Incentive Cannibalization in E-commerce Uplift Modeling
2026-07-06 • Machine Learning
Machine LearningArtificial IntelligenceInformation Retrieval
AI summaryⓘ
The authors studied how to better give shopping incentives on platforms with many sellers, where typical methods struggle because shoppers might just shift spending between stores instead of buying more overall. They identified two problems: incentives causing buyers to move shopping around (cannibalization) and noisy data from organic purchases or other rewards. To fix this, they created CanniUplift, a system that looks at sales across the whole platform to account for seller competition and uses customer redemption data to reduce noise. Their tests, including real online experiments, showed this method improves sales growth and return on investment compared to previous approaches.
uplift modelingindividual treatment effect (ITE)Stable Unit Treatment Value Assumption (SUTVA)cannibalizationincentive allocationincrementality estimationredemption behaviorwAUUCwQINIA/B testing
Authors
Zuwang He, Shihao Shu, Yuli Qu, Hanyu Gao, Ziliang Zhang, Diwei Chen, Xiangda Yan, Buyu Gao, Tanchao Zhu, Yumeng Li, Junxiong Zhu
Abstract
Personalized incentive allocation is vital for e-commerce, where uplift modeling is the standard for estimating Individual Treatment Effects (ITE). However, traditional models often fail in complex multi-seller environments with violations of the Stable Unit Treatment Value Assumption (SUTVA). We identify two critical challenges: Seller-level Cannibalization, where incentives shift expenditure between shops without growing the platform, and Incentive-level Cannibalization, where organic conversions or alternative rewards introduce significant noise into incrementality estimation. In this paper, we propose CanniUplift, a unified framework to mitigate these dual-source cannibalization effects. Specifically, we design Platform-level Global Alignment (PGA) to capture cross-shop substitution through global GMV consistency constraints. To tackle incentive-driven noise, we introduce Redemption-based Decomposition Denoising (RDD), which uses redemption behavior to decompose treated outcomes and reduce attribution noise within an entire-space framework. Furthermore, a Treat-Attention mechanism is designed to model intricate interactions between users' historical behaviors and current treatment options. Extensive experiments on both synthetic and large-scale industrial datasets demonstrate that CanniUplift significantly outperforms state-of-the-art baselines. Ablation studies confirm that the integration of PGA and RDD consistently improves wAUUC and wQINI. Successfully deployed online, our framework achieved a 4.08% relative increase in platform-wide incremental GMV (Delta GMV) over the production baseline and improved ROI in online A/B tests, proving effective in driving global platform growth.