Data Science and Machine Learning in mathematics education: Highschool students working on the Netflix Prize

Sarah Schönbrodt (1) , Martin Frank (1)

1 KIT - Karlsruhe Institute of Technology

One goal of contemporary mathematical modeling classes in schools should be to include up-to-date problems or interesting, new technologies from the everyday life of students-especially if these allow the didactical reduction to elementary (school-)mathematical knowledge and thus have the potential to enrich mathematics education. Data Science and Machine Learning is applied in numerous areas of science and technology and used in many applications in our everyday life. Using movie recommender systems and the so-called Netflix Prize as an example, this paper discusses how mathematics education can be enriched by modeling real-world, student-centered problems from the field of Machine Learning in school. For this purpose, we describe tested digital learning material from guided modeling projects and share our experience with giving the problem of developing a recommender system as a completely open problem to upper secondary students.

Mots clés: Data Science; Machine Learning; mathematical modeling; recommender system; digital learning material

Domaines: Mathématiques [math]

Sarah Schönbrodt, Martin Frank. Data Science and Machine Learning in mathematics education: Highschool students working on the Netflix Prize. Twelfth Congress of the European Society for Research in Mathematics Education (CERME12), Feb 2022, Bozen-Bolzano, Italy. ⟨hal-03754716⟩