Abstract: 

In this talk, we will explore and demystify th world of Causal AI for data science practitioners, with a focus on understand cause-and-effect relationships within data to drive optimal decisions. In this talk, we will focus on:

* from shapley to DAGs: the dangers of using post-hoc explainability methods as tools for decision making, and how tranditional ML isn't suited in situations where want to perform interventions on the system.
* discovering causality: how do we figure out what is causal and what isn't, with a brief introduction to methods of structure learning and causal discovery
* optimal decision making: by understanding causality, we now can accurately estimate the impact we can make on our system - how to use this knowledge to derive the best possible actions to make?

This talk is aimed at both data scientists and industry practitioners who have a working knowledge of traditional statistics and basic ML. This talk will also be practical: we will provide you with guidance to immediately start implementing some of these concepts in your daily work.

Session Outline:

* from shapley to DAGs: the dangers of using post-hoc explainability methods as tools for decision making, and how tranditional ML isn't suited in situations where want to perform interventions on the system. In this module, we will start with a standard Kaggle-like dataset, perform ML task and interpret results - showcasing why ML fails at such tasks. We will also introduce causal diagrams and causal effect estimation.

* discovering causality: how do we figure out what is causal and what isn't, with a brief introduction to methods of structure learning and causal discovery. In this section we will cover a number of algorithms which are available open-source, showing how to go from data to causal diagrams.

* optimal decision making: by understanding causality, we now can accurately estimate the impact we can make on our system - how to use this knowledge to derive the best possible actions to make? In this section, we will again use open-source algorithms to show how the knowledge of a causal diagram can be used to help get the best interventions to uplift a set of business KPIs.

Learning objectives:
causal effect estimation and causal discovery algorithms (doWhy, gCastle, causal-learn, etc). As well as new methods not available open-source.

Background Knowledge:

Fundamental statistics (correlations & OLS)

Bio: 

Andre joined causaLens from Goldman Sachs, where he was an executive director in the Model Risk Management group in Hong Kong and Frankfurt. Today he is working with industry leading, global organisations to apply cutting edge Causal AI research in production level solutions that empower individuals and teams to make better decisions. Andre received his PhD in theoretical physics from the University of Munich, where he studied the interplay between quantum mechanics and general relativity in black-holes.