About

Beyond Correlations and Regressions

Traditional data science often stops at correlations, p-values, and associative models. Causalica is about taking the next step: understanding the underlying mechanisms that drive outcomes.

We leverage cutting-edge tools for causal inference—moving from “what happened” to “why it happened” and “what if we change this?”

The Causalica Approach

Our work focuses on three pillars:

1. Structural Causal Models (SCMs): We build explicit frameworks to map out causal assumptions, moving beyond the limitations of simple regressions to capture the complexity of real-world systems.
2. AI-Enhanced Discovery: We use AI not just for prediction, but as a lever to scale causal discovery and automate the identification of potential causal links in high-dimensional data.
3. Decision-Centric Workflows: Causal inference isn’t just a theoretical exercise. Our goal is to aid decision-making by providing robust estimates of treatment effects and counterfactual scenarios.

What You’ll Find Here

• Research-Grade Workflows: Practical implementations of causal techniques (Double ML, Synthetic Control, IV, etc.) applied to real-world problems.
• A Living Textbook: My ongoing journey to document the theory and practice of causal inference in a digestible, AI-ready format.
• Practical Notes: Snippets, mental models, and hands-on tutorials for practitioners who want to move beyond p-hacking to principled decision science.

Causalica is a space for those who want to build the future of decision-making, one cause at a time.