SICSS-ODISSEI

ODISSEI-SICSS is split into two phases. During the first week, the participants will be introduced to ODISSEI and taught machine learning in Python. This will be primarily done through a course run by the eScience center. In the second week of the summer school, participants will be able to make full use of the ODISSEI infrastructure, during which they will be put into teams and challenged to work on research projects. Each team will be provided with access to FIRMBACKBONE, containing detailed data on Dutch companies, through the secure environment SANE. Specifically, researchers will get access to the corporate trade register, employment surveys, financial data, emission data, and indicators derived from websites.

FIRMBACKBONE is a treasure trove of data which can help us predict important outcomes. The teams will compete to develop effective predictive models to answer innovative research questions. This challenge will help participants get a more hands-on experience of computational social science research with some of the most advanced data infrastructure available.

At the end of most days of the summer school, there will be a guest speaker who will present their work or a general topic in computational social science to the participants. These talks will last 20-30 mins with 15-20 mins of Q&A. Slides will be added on the ODISSEI Zenodo Community; other material will be shared via GitHub.

All course sessions will take place in the Sanders Building on the Erasmus Campus Woudestein, Burgemeester Oudlaan 50, Rotterdam. You can find information here and download the campus map here. Throughout the summer school, ODISSEI will organize various social events. Read more about those in the timetable below. Each day will have three breaks. A coffee break in the morning, lunch at 12:00, and another coffee break in the afternoon.

10:00-12:00: Introducing ODISSEI and Computational Social Science. Speaker: Tom Emery

12:00-13:00: Lunch break

13:00-15:00: Introduction to FIRMBACKBONE

15:00-16:30: Introduction to SANE. Speaker: Tom Emery

Social Event (17:00-19:00): Opening Drinks TBA

Location: Room:3.09, Polak building

09:00-17:00: more detailed schedule of the day will be available shortly

12:00-13:00: Lunch break

16:00-17:00: Guest lecture TBA

Location: Room:3.09, Polak building

09:00: Welcome and icebreaker

09:15: Introduction to machine learning

10:00: Break

10:10: Tabular data exploration

11:00: Break

11:10: Fitting a scikit-learn model on numerical data

12:00-13:00: Lunch break

13:00: Fitting a scikit-learn model on numerical data

14:00: Break

14:10: Fitting a scikit-learn model on numerical data

15:00: Break

15:10: Cross-validation

15:45: Wrap-up

16:00-17:00: Guest lecture: TBA

Location: Room:3.09, Polak building

09:00: Welcome and recap

09:15: Handling categorical data

10:00: Break

10:10 Using numerical and categorical variables together

11:00: Break

11:10: Intuitions on decision trees

11:30: Overfitting and underfitting

12:00-13:00: Lunch break

13:00: Validation and learning curves

13:30: Advanced topics

14:00: Break

14:10: Try out learned skills on new dataset

15:00-16:00: Guest lecture TBA

16:10: Concluding remarks

16:45: Wrap-up & Post-workshop Survey

Social Event (17:30-20:00): TBA

Location: Room:3.09, Polak building

09:00-17:00: more detailed schedule of the day will be available shortly

12:00-13:00: Lunch break

Location: Room:3.14, Polak building

10:00-11:00: Introducing the Data Challenge

11:00-12:00: Getting into SANE

13:00-17:00: Research project

12:00-13:00: Lunch break

Location: Room:3.09, Polak building

09:00 - 17:00 Research project

12:00-13:00: Lunch break

Location: Room:3.09, Polak building

09:00 - 17:00 Research project

12:00-13:00: Lunch break

Location: Room:3.09, Polak building

09:00 - 17:00 Research project

12:00-13:00: Lunch break

Location: Room:3.09, Polak building

Closing dinner TBA

09:00 - 12:00 Research project

12:30 - 17:00 Presentations

12:00-13:00: Lunch break

Location: Room:3.09, Polak building