Research Prototype · Ground Truth Validated

AI-Powered
Causal Inference

Automatically separate correlation from causation. AutoML + Double Machine Learning uncovers the real causes hidden in your data and provides actionable insights.

Scenario A: Credit Limit

Optimize credit limits to minimize default rates.

Credit Limit
Default Rate
Income

Scenario B: Medical Treatment

Healthcare outcome analysis with confounding variables

Treatment Effect
Patient History
Cure Rate
REAL DATA

Scenario C: Personal Career

Analyze causal impact of your skills on market value based on local knowledge base.

Skill Level
Project Completion
Market Value
Start AnalysisGitHub Repository

AI AutoML Causal Inference

AI auto-selects the optimal model between LinearDML and CausalForest. RMSE 0.028–0.609, Correlation 0.977–0.996.

Causal Graph (DAG)

Automatically discover causal structures with the PC Algorithm. Visually identify confounders, treatment, and outcome variables.

What-If Decision Making

'Will raising the credit limit reduce defaults?' — Ground truth validated counterfactual simulation.