The Digital Epidemiology Lab currently offers some projects for semester or master thesis projects.

If you are interested in working on one of the projects listed below, please send an email to the projects’ contact in which you answer the following questions:

• Which project(s) are you interested in?
• Are you looking for a thesis or a semester project? Priority will be given to Master Thesis Projects (full time).
• Why did these specific projects catch your attention?
• How much time could you spend on the project per week? How many classes are you planning on taking in addition to the project?
• Please attach your CV and links to projects you developed (e.g. GitHub repo).

(You can find logistic info on IC semester projects here; and on Master’s thesis projects here.)

Our lab is developing, maintaining and improving a platform for open data science challenges: crowdAI.org. Thousands of users compete on different problems in Machine Learning and Artificial Intelligence on this platform.

The primary feedback that participants get after submitting a solution to a problem is a score on the leaderboard of a particular challenge. We believe that the engagement of challenge participants can be greatly increased if we provide more generalised feedback about their own performance in the challenge and confront them to solution from other participants.

The goal of this project is to find interesting statistics to capture for a crowdAI challenge, and presenting it to the users in an easily digestible way.
For instance, the overall score distribution at any point of time can be visualized using something along the lines of:

or, the overall progression of the scores of each participants over time can be visualized as:

Our lab is developing, maintaining and improving a platform for open data science challenges: crowdAI.org. Thousands of users compete on different problems in Machine Learning and Artificial Intelligence on this platform.

Social networks reply on user participation, and many are based around some form of reputation system. At crowdAI we have already attached significant user engagement in the form of code contributions and forum topics and posts. We want to take the level of user engagement to the next level, and at the same time reward our key contributors in the form of an online reputation system.

The goal of this semester project would be to design, prototype and A/B test a comprehensive reputation system for crowdAI. We are inspired by the very different but all quite successful systems in play at: Stack Overflow, GitHub or Quora. A sharable display of a user’s reputation, such as Stack Overflow’s Flair could also be one of the approach.
You will work closely with the crowdAI developers and UI designers, and we hope that you will design and build part, or all, of the reputation system by the end of your placement.