M2.1.P Preparation FMP

The aim of the project is to help people reimagine their relationship with recommender systems. By showing a reimagined recommender system in an unfamiliar way, I wanted to see if people could talk about the complexity of recommender systems.  


This project took place at an external research group for recommender systems at Technische Universität Wien. It was an important project because it threw me out of my comfort zone at TU/e into an environment in which no one understood me. The main things that I learned were:

  1. Some of the data scientists in Vienna knew really well how to protect their data privacy 
  2. How to explain design methods to students from other expertise

Coaches: Kristina Andersen, Julia Neidhardt and Peter Knees

Partner: TU Wien, Austria

Grade: P

Expertise Areas: Technology and Realization, Creativity and Aesthetics, User and Society, Math, Data and Computing, Design and research processes

What was the impact of my stay at TUW?

Peter Knees: ”You gave them a bigger perspective, which they usually don’t have at the undergrad level, and just for that reason it was important because now people are thinking more about what they’re doing and how it connects and what the implications might be. But thinking about what this actually entails and what it leads to in the beginning is exactly the kind of approach we wanna have. Also, for our algorithm design. So this is exactly what we needed.” 

Future work together

The creation of a workshop for highschool students at a school in Vienna. The issue for them is that they have no knowledge about the ethical implications of using ChatGPT in their school education. Together, a team of data scientists and I will work on an interactive workshop to educate the students about it. 

Explanation of the recommender system

Created with Pia Pachinger and Ignacio Baltazar Pérez-Messina,