Prof. Dr. h.c. Hasso Plattner

# Causal Inference - Theory and Applications in Enterprise Computing

## Short Description

The questions that motivate most data analysis are not associational but causal in nature. What are the causes and what are the effects of events under observation? Nevertheless, the statistical methods commonly used today to answer those questions are of associational nature. But “Correlation does not imply causation!”, and misinterpretation often results in incorrect deduction.

In the recent years, causality has grown from a nebulous concept into a mathematical theory. This is largely due to the work of Judea Pearl (2009) who has received the 2011 Turing Award for “fundamental contributions to artificial intelligence through the development of a calculus for probabilistic and causal reasoning”.

In this lecture, you look at the mathematical concepts that build the basis of causal inference and how they can be used to derive causal relationships from observational data. After you gained an overview on the needed concepts, you will work on particular tasks in the context of the causal inference procedure. Moreover, you will present your work and write a scientific report about your implementation results.

## Goals of the Course

• Understand...

• opportunities of causal inference
• the mathematical concepts
• challenges and problems in the context of real-world applications
• constraint-based algorithms to derive causal relationships

• Do...

• work in small teams
• work on a specific topic in the context of data-driven causal inference
• implement algorithms and analyze performance results
• write a scientific report

• Improve...

• mathematical, analytical, and modeling skills
• scientific working and writing
• machine learning techniques

## Preconditions

• the participants should be interested in mathematical methods

## Grading

• 50 % Implementation and presentation of results
• 40% Scientific report
• 10% Personal engagement

## Dates & Topics

 Date Topic Slides 09.04.2019 Lecture Overview and Causal Inference in a Nutshell Causal_Inference-Theory_and_Applications 10.04.2019 Causality in Application and Lecture Example Causality_in_Application 16.04.2019 Introduction to Causal Graphical Models Introduction_to_Causal_Graphical_Models 17.04.2019 Introduction to Conditional Independence Testing (I/II) Introduction_to_Conditional_Independence_Testing 23.04.2019 Introduction to Conditional Independence Testing (II/II) 24.04.2019 Introduction to Constraint-Based Causal Structure Learning Introduction_to_Constraint-Based_Causal_Structure_Learning 30.04.2019 Topic Discussions and Individual Meetings 07.05. - 21.05.2019 Individual Meetings 28.05.2019 Intermediate Presentation 29.05.2019 Individual Presentation Recap and Next Steps 04.06.2019 Introduction to Causal Calculus (I/II) Introduction_to_Causal_Calculus 05.06.2019 Introduction to Causal Calculus (II/II) 11.06. - 02.07.2019 Individual Meetings 03.07.2019 Final Presentation 16.07.2019 Scientific Writing Scientific Writing 05.08.2019 Draft Submission 16.08.2019 Review Submission 30.08.2019 Final Submission