Jointly Optimizing Debiased CTR and Uplift for Coupons Marketing: A Unified Causal Framework
Siyun Yang, Shixiao Yang, Jian Wang, Di Fan, Kehe Cai, Haoyan Fu, Jiaming Zhang, Wenjin Wu, Peng Jiang
TL;DR
UniMVT addresses confounding bias in CTR when coupons serve as multi-valued interventions by unifying disentangled representation learning with full-space counterfactual inference. The framework couples a Deconfounded Causal Representation (DCR) built on Mixture-of-Experts with a Heterogeneous Treatment Effect Network (HTE Net) that decouples base CTR and uplift while enforcing a monotonic linear uplift relationship. A Counterfactual X-Network, intensity projection, and orthogonality regularization ensure robust uplift estimation across continuous treatment intensities and across treated/control groups, with theoretical convergence guarantees. Extensive offline experiments on synthetic and industrial data, plus real-world online A/B tests, demonstrate improvements in both CTR calibration and uplift-driven coupon optimization, translating to meaningful business gains in production.
Abstract
In online advertising, marketing interventions such as coupons introduce significant confounding bias into Click-Through Rate (CTR) prediction. Observed clicks reflect a mixture of users' intrinsic preferences and the uplift induced by these interventions. This causes conventional models to miscalibrate base CTRs, which distorts downstream ranking and billing decisions. Furthermore, marketing interventions often operate as multi-valued treatments with varying magnitudes, introducing additional complexity to CTR prediction. To address these issues, we propose the \textbf{Uni}fied \textbf{M}ulti-\textbf{V}alued \textbf{T}reatment Network (UniMVT). Specifically, UniMVT disentangles confounding factors from treatment-sensitive representations, enabling a full-space counterfactual inference module to jointly reconstruct the debiased base CTR and intensity-response curves. To handle the complexity of multi-valued treatments, UniMVT employs an auxiliary intensity estimation task to capture treatment propensities and devise a unit uplift objective that normalizes the intervention effect. This ensures comparable estimation across the continuous coupon-value spectrum. UniMVT simultaneously achieves debiased CTR prediction for accurate system calibration and precise uplift estimation for incentive allocation. Extensive experiments on synthetic and industrial datasets demonstrate UniMVT's superiority in both predictive accuracy and calibration. Furthermore, real-world A/B tests confirm that UniMVT significantly improves business metrics through more effective coupon distribution.