The consumption of mozzarella per person and the number of PhDs in civil engineering in the United States have been rising at a similar pace since the year 2000. However, if you start eating mozzarella instead of drinking alcohol upon reaching the drinking age, that will not automatically make you a successful doctoral student. This example shows that even though we live in a world drowning in data, extracting the relevant bits from it can be quite a challenge.

The data science course is intended for anyone who wants to learn how to identify, understand and show interesting information from data. Here’s what you can expect:

• You’ll literally get your hands dirty with several datasets spanning retail, housing, meteorology, healthcare or finance, and learn the basics of data analysis and visualisation using Python and the Pandas library.
• You’ll make a simple model for predicting house prices based on their size, air quality, crime rate, or school accessibility in their location.
• We’ll explore some paradoxes, such as how analysing large amounts of data can lead to opposite results than examining its individual parts – such a misunderstanding of data even led to a lawsuit against the University of Berkeley!
• You’ll see more examples like the one with mozzarella above and learn to distinguish correlation from causation.
• And finally, we’ll see how AI can currently perform data analysis for us (and chat whether it will eventually make data scientists obsolete)!

Don’t worry if you haven’t coded before: our work in Python will be like manipulating tables in Excel, but in a much more efficient way. The important thing is that you are comfortable thinking in numbers and enjoy interpreting data in various tables and graphs. You will certainly enjoy the course if you’ve already studied some statistics and liked it, or if you are interested in any data-driven discipline, such as business, economics, finance, experimental physics or even biology!