This $160,000 National Science Foundation project grant supports research at Cornell University to develop cutting-edge machine learning methods for causal inference with high-dimensional complex data through 2026. Funded under the Mathematical and Physical Sciences program (CFDA 47.049), the research aims to address theoretical, methodological and computational challenges of drawing causal conclusions from vast datasets. Specific projects include proposing a covariate balancing methodology coupled with modern machine learning for efficient causal analysis, optimally distributed covariate balancing for massive heterogeneous data, and a sequential approach for marginal structural models in longitudinal studies. A theme is using covariate balancing, which balances covariates if the propensity score estimates balance them. This award advances the program's goals of strengthening the nation's scientific enterprise through increasing mathematical and physical sciences knowledge and understanding major national problems.