Double Machine Learning
A causal inference method that fits machine learning models to outcome and treatment variables and, combined with orthogonalization and cross-fitting, eliminates regularization bias to produce robust estimates of treatment effects.
Timeline (last 90 days)
The core idea of DML is to use machine learning models to separately fit the outcome variable and the treatment variable, then eliminate regularization bias through orthogonalization (Neyman orthogonality) and cross-fitting, thereby obtaining an unbiased and √n-consistent estimator.
The study proposes a causal machine learning framework based on Double Machine Learning to estimate zone-type-specific treatment effects (commercial zones vs residential zones).
All Facts (2)
The core idea of DML is to use machine learning models to separately fit the outcome variable and the treatment variable, then eliminate regularization bias through orthogonalization (Neyman orthogonality) and cross-fitting, thereby obtaining an unbiased and √n-consistent estimator.
50%UnverifiedThe study proposes a causal machine learning framework based on Double Machine Learning to estimate zone-type-specific treatment effects (commercial zones vs residential zones).
50%