Causal Data Science Lab @UIUC

I am Yonghan Jung, an assistant professor in the School of Information Sciences at UIUC and the leader of the Causal Data Science Lab. I am also a faculty affiliate at the National Center for Supercomputing Applications (NCSA) and Illinois Informatics.

Our lab studies Pragmatic Causal Inference: methods that make causal questions as usable as prediction workflows while keeping assumptions, uncertainty, and validity explicit. A data scientist often wants to know what would happen if an action changed. Answering that question requires more than prediction; it requires a causal workflow that can reason about assumptions, identify what is learnable, estimate it reliably, and support decisions.

Lab GitHub

The lab’s public code and reproducibility artifacts are hosted at CausalDataScience.

Our current research is organized around four connected directions:

1. Partial Identification: valid causal answers under weak assumptions, including bounds and sensitivity analyses when point identification is not justified.

2. Practical Causal Learning: estimators and workflows for causal questions under mild, decision-relevant assumptions such as front-door, proxy, mediator, or overlap structure.

3. Amortized Causal Inference: simulation, pretraining, and scalable algorithms that reduce repeated graph, identification, and estimation burdens.

4. Real-World Deployment: causal systems for biomedical digital twins, health decisions, and other settings where causal answers must support action.