Application of Machine Learning method based Estimation of Heterogeneous Treatment Effects in Economics

Wang, Xia; Huang, Xiaoyan; Zhang, Yun

doi:10.1145/3570236.3570262

Cited by 1 publication

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2 below). Through causal relationship examination, we observe that the attributes of users and coupons related to marketing tactics can impact both the conversion probability and user-coupon representations, resulting in a confounding bias in the causal inference literature (Grimes and Schulz 2002;VanderWeele, Hernán, and Robins 2008;Tang et al 2023Tang et al , 2022. Therefore, we transform the problem of mitigating matching bias to adjusting for the confounding effect, as described formally in Section Methods.…”

Section: Introductionmentioning

confidence: 99%

Backdoor Adjustment via Group Adaptation for Debiased Coupon Recommendations

Fang,

Zhang,

Cui

et al. 2024

AAAI

View full text Add to dashboard Cite

Accurate prediction of coupon usage is crucial for promoting user consumption through targeted coupon recommendations. However, in real-world coupon recommendations, the coupon allocation process is not solely determined by the model trained with the history interaction data but is also interfered with by marketing tactics desired to fulfill specific commercial goals.This interference creates an imbalance in the interactions, which causes the data to deviate from the user's natural preferences. We refer to this deviation as the matching bias. Such biased interaction data affects the efficacy of the model, and thus it is necessary to employ debiasing techniques to prevent any negative impact. We investigate the mitigation of matching bias in coupon recommendations from a causal-effect perspective. By treating the attributes of users and coupons associated with marketing tactics as confounders, we find the confounders open the backdoor path between user-coupon matching and the conversion, which introduces spurious correlation. To remove the bad effect, we propose a novel training paradigm named Backdoor Adjustment via Group Adaptation (BAGA) for debiased coupon recommendations, which performs intervened training and inference, i.e., separately modeling each user-coupon group pair. However, modeling all possible group pairs greatly increases the computational complexity and cost. To address the efficiency challenge, we further present a simple but effective dual-tower multi-task framework and leverage the Customized Gate Control (CGC) model architecture, which separately models each user and coupon group with a separate expert module. We instantiate BAGA on five representative models: FM, DNN, NCF, MASKNET, and DEEPFM, and conduct comprehensive offline and online experiments to demonstrate the efficacy of our proposed paradigm.

show abstract

Section: Introductionmentioning

confidence: 99%