The proposed C-XGBoost model exploits the strong prediction abilities of XGBoost algorithm and the ability of causal inference neural networks to learn representations useful for estimating outcomes in both treatment and control groups, resulting in an effective tree-based ensemble model for causal effect estimation.
Random Hyperplane Tessellations (RHPT) provide an efficient and effective approach for estimating causal effects from high-dimensional observational data, outperforming traditional matching techniques and being competitive with state-of-the-art deep learning methods.