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

Key Points

• The central aim is to develop a method for estimating heterogeneous treatment effects in the context of content creator selection.
• Developed a Deep-DiD method integrating deep neural networks with a difference-in-differences framework.
• Applied the method to analyze platform creator selection processes.
• Successfully estimated heterogeneous treatment effects using the developed method.
• Demonstrated the potential of the method for optimizing content creator selection on platforms.