Mozilla Festival 2021 (March 8th – 19th, 2021)

Mozilla Festival 2021 (March 8th – 19th, 2021)

Let's demolish my thesis: Is using Machine Learning to predict student failure a good idea?

Life at the Faculty of Engineering of the National University of Asunción is tough. With around 12.000 class inscriptions every semester, only around 6.000 end up with a passing grade. This, combined with the institutional weakness that characterizes Paraguayan state institutions and regular heat waves (and regular power cuts), creates a very tense environment for students, teachers and authorities alike.

As I was choosing a research topic to finish off my time in university as an engineering student at this very university, I was offered the opportunity to work on a prediction, binary classification and ranking system using Data Science and Machine Learning. What exactly am I predicting? Student failure.

In this session, we will explore how this system is designed and discuss who it really benefits: the students, the faculty, or the system itself.


We're hoping that many efforts and discussions will continue after Mozfest. Share any ideas you already have for how to continue the work from your session.:

I think pretty much any technology concerning AI can be analyzed in the way that I plan for this session. I would love it if we could form a community of people who want to debate on these issues.

How will you deal with varying numbers of participants in your session?:

The use of sticky notes to share opinions should allow people to participate in parallel. If the number of people were very low, I would still use the sticky notes but try and start an actual conversation with the participants.

I'm an engineering student, feminist and human rights activist. I work in digital fabrication, education, research and starting to transition into data science and machine learning.