VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.
Building a Robot Judge: Data Science for Decision-Making
Last Updated: 2026-02-05 15:35:41
Abstract
This course explores the automation of decisions in the legal system. We delve into the machine learning tools needed to predict judge decision-making and ask whether techniques in model explanation and algorithmic fairness are sufficient to address the potential risks.
Objective
This course introduces students to the data science tools that may provide the first building blocks for a robot judge. While building a working robot judge might be far off in the future, some of the building blocks are already here, and we will put them to work.
Content
Data science technologies have the potential to improve legal decisions by making them more efficient and consistent. On the other hand, there are serious risks that automated systems could replicate or amplify existing legal biases and rigidities. Given the stakes, these technologies force us to think carefully about notions of fairness and justice and how they should be applied. The focus is on legal prediction problems. Given the evidence and briefs in this case, how will a judge probably decide? How likely is a criminal defendant to commit another crime? How much additional revenue will this new tax law collect? Students will investigate and implement the relevant machine learning tools for making these types of predictions, including regression, classification, and deep neural networks models. We then use these predictions to better understand the operation of the legal system. Under what conditions do judges tend to make errors? Against which types of defendants do parole boards exhibit bias? Which jurisdictions have the most tax loopholes? Students will be introduced to emerging applied research in this vein. In a semester paper, students (individually or in groups) will conceive and implement an applied data-science research project.
General Information
- Language
- English
- Levels
- DS , DR , MSC
- Frequency
- Yearly recurring
Examination
- Type
- graded semester performance
Course Components
| Type | Title | Time & Place | Hours |
|---|---|---|---|
| lecture |
Building a Robot Judge: Data Science for Decision-Making
The lecturers will communicate the exact lesson times of ONLINE courses.
|
|
2 h weekly |
Offered In
-
GESS Science in Perspective (Only the topics listed in this paragraph can be chosen as GESS Science in Perspective. Further below you will find the "type B courses Reflections about subject specific methods and content" as well as the language courses. 6 ECTS need to be acquired during the BA and 2 ECTS during the MA Students who already took a course within their main study program are NOT allowed to take the course again.)
-
Type A: Enhancement of Reflection Competence (Suitable for all students. Students who already took a course within their main study program are NOT allowed to take the course again.)
-
Type B: Reflection About Subject-Specific Methods and Contents (Subject-specific courses: Recommended for doctoral, master and bachelor students (after first-year examination only). Students who already took a course within their main study program are NOT allowed to take the course again. These course units are also listed under "Type A", which basically means all students can enroll)
-
-
Doctoral Department of Humanities, Social and Political Sciences (More Information at: )
-