Applied Causal AI

Hands-on Workshops for Data Scientists

This program answers: Why traditional ai is not made for causal estimation? How causal inference can help? What is causal AI and how to use it?

Participants will learn practical approaches for designing and implementing A/B tests and explore quasi-experimental methods to uncover causal relationships when randomization isn’t feasible. Through hands-on guidance, industry data teams will gain the skills to apply these techniques effectively in real-world scenarios.

Practical Training for Industry Data Teams

Part I : Predictive vs. Causal inference

Understand the difference between predictive and causal inference to know when to use traditional ML, causal inference and causal ML.

Part II : A/B testing

While randomization is often called the Gold Standard for measuring causal effects, it is full of challenges. Learn how to implement it efficiently and safely.

Part III : Quasi-experimental methods

Complement your toolkit with quasi-experimental methods, enabling you to measure causal effects when randomization is not possible or has significant limitations.

Start the revolution today

Flexible format

🕒 Duration: 2 hours to several days

📣 Format: Online or on-site

🏷️ Price: 4000 USD / half day

💬 Language: FR or EN

The workshop content is customized to align with the participants' existing knowledge and the client's specific objectives.

Potential subjects

Causal vs. Predictive inference
Directed Graphs
Potential outcomes
Good and Bad Controls
A/B testing
Double Machine Learning and Causal Forest
Quasi-experimental methods
- Fixed Effects
- Difference-in-Difference
- Synthetic Control Method
- Instrumental Variable
- and more