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

Marketing Science 2026

View at publisher
Authors: Yan Cheng, Jingbo Wang, Xinyu Cao, Zuo-Jun Max Shen, Yuhui Zhang
DOI: 10.1287/mksc.2023.0511
Cited by: 1
References: 53

Abstract

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.

Fields of Study & Subjects

Advanced Causal Inference Techniques Meta-analysis and systematic reviews Explainable Artificial Intelligence (XAI)

Publication details

Journal / source
Marketing Science
Publisher
Institute for Operations Research and the Management Sciences (INFORMS)
Volume
45
Issue
2
Pages
258–279
Publication date
14 January 2026
Language
EN