Search Results for author:
Found 2 papers, 1 papers with code
The impact of heteroskedasticity on uplift modeling
In our research, we show that heteroskedastictity in the training data can cause a bias of the uplift model ranking: individuals with the highest treatment effects can get accumulated in large numbers at the bottom of the ranking.
Improving uplift model evaluation on RCT data
We theoretically analyze the variance of uplift evaluation metrics and derive possible methods of variance reduction, which are based on statistical adjustment of the outcome.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
