A Deep-DiD Method to Estimate Heterogeneous Treatment Effects: Application to Content Creator Selection

This paper develops a Deep-DiD method that integrates two deep neural networks into a difference-in-differences framework to estimate heterogeneous treatment effects and applies it to optimizing platform creator selection.

• 저널Marketing Science · 45(2) · 258–279
• 토픽Advanced Causal Inference Techniques · Statistics and Probability
• DOI10.1287/mksc.2023.0511
• 저자Cheng Yan, Jingbo Wang, Xinyu Cao, Zuo‐Jun Max Shen, Yuhui Zhang