Nino Antulov-Fantulin: Catalogue data in Spring Semester 2021
|Name||Dr. Nino Antulov-Fantulin|
Computational Social Science
ETH Zürich, STD F 4
|Telephone||+41 44 632 61 57|
|Department||Humanities, Social and Political Sciences|
|851-0585-38L||Data Science in Techno-Socio-Economic Systems |
Number of participants limited to 80
This course is thought be for students in the 5th semester or above with quantitative skills and interests in modeling and computer simulations.
Particularly suitable for students of D-INFK, D-ITET, D-MAVT, D-MTEC, D-PHYS
|3 credits||2V||D. Helbing, N. Antulov-Fantulin, V. Vasiliauskaite|
|Abstract||This course introduces how techno-socio-economic systems in our complex society can be better understood with techniques and tools of data science. Students shall learn how the fundamentals of data science are used to give insights into the research of complexity science, computational social science, economics, finance, and others.|
|Objective||The goal of this course is to qualify students with knowledge on data science to better understand techno-socio-economic systems in our complex societies. This course aims to make students capable of applying the most appropriate and effective techniques of data science under different application scenarios. The course aims to engage students in exciting state-of-the-art scientific tools, methods and techniques of data science. |
In particular, lectures will be divided into research talks and tutorials. The course shall increase the awareness level of students of the importance of interdisciplinary research. Finally, students have the opportunity to develop their own data science skills based on a data challenge task, they have to solve, deliver and present at the end of the course.
|Content||Will be provided on a separate course webpage.|
|Lecture notes||Slides will be provided.|
|Literature||Grus, Joel. "Data Science from Scratch: First Principles with Python". O'Reilly Media, 2019.|
"A high-bias, low-variance introduction to machine learning for physicists"
Applications to Techno-Socio-Economic Systems:
"The hidden geometry of complex, network-driven contagion phenomena" (relevant for modeling pandemic spread)
"A network framework of cultural history"
"Science of science"
"Generalized network dismantling"
Further literature will be recommended in the lectures.
|Prerequisites / Notice||Good programming skills and a good understanding of probability & statistics and calculus are expected.|