Every July, Nijmegen turns orange and green. Mees van Galen knows this better than anyone: he was born in Nijmegen, has always lived there, and is now studying for a Master’s degree in Data Science at Radboud University.
Don’t automate 100%
During the 4Daagse and the accompanying Vierdaagsefeesten, the city celebrates for seven days. More than 3,000 artists (including many well-known names such as Lil’ Kleine, Tino Martin, Yves Berendse, Snollebollekes and Jan Smit) give 1,000 free performances across 46 stages throughout the city. These performances attract 1.1 million visitors, resulting in major crowds in the city centre. It is the responsibility of 'Stichting Vierdaagsefeesten' to manage this safely and ensure that safety remains the top priority. That is quite a challenge. Yet AI student Mees van Gaalen immediately had some ideas: “Try not to automate something as important as safety 100%.”
So how did 'Stichting Vierdaagsefeesten' work up until then? Mees can now explain it in detail: “Before I could carry out the assignment, I first got to know the organisation and its way of working better. The organisers of each stage would initially send their preferred schedule separately to 'Stichting Vierdaagsefeesten'. They then collected all the schedules in one large file and manually reviewed it for potential safety risks.”
Safety risks
There are three key risks to consider when programming artists and locations. First, an artist may be so popular that the square in front of the stage is too small. Think of Snollebollekes, for example, when more than 450,000 visitors earlier this year were jumping from side to side at the GelreDome in Arnhem. Mees explains: “Because the Vierdaagsefeesten are free to attend, there is no ticketing system and therefore no limit on how many tickets could be sold.”
Another potential problem arises when two or more artists in the same genre perform shortly after one another on different stages. This can create a large flow of people walking through the city. Finally, an artist may have appeared negatively in the media, which could result in angry festivalgoers attending the performance.
Mees: “My assignment was to develop software that automatically checks their schedule based on the potential safety risks described above.”
The biggest challenge was making the software as user-friendly as possible. Mees explains: “This is my first assignment where I delivered something for actual use. So you want it to be as easy as possible for employees of 'Stichting Vierdaagsefeesten' to use.”
The tool indicates an artist’s popularity, among other things by looking at the number of Spotify streams. After completing the assignment, Mees emphasised to the users that his AI tool is only a supporting tool. “The application only makes recommendations and ensures that the 90% of acts that would pose ‘no risk’ are filtered out, so that the remaining 10% can be carefully checked manually.”
NOS News
He really enjoyed putting his knowledge to use for an organisation in Nijmegen, his hometown. “I’ve always lived here, and as a musician I also perform at the Vierdaagsefeesten myself. So I was quite proud to be able to contribute to the organisation of the Vierdaagsefeesten. It gives you the opportunity to see how an organisation like this operates, and I find that really interesting!”
The AI tool that Mees developed in collaboration with 'Stichting Vierdaagsefeesten' was even featured on the NOS News. Watch the segment here (from 14:12 onwards).
What is MKB Datalab-Oost?
MKB Datalab-Oost introduces entrepreneurs to AI and data-driven business in an accessible way. It does this through inspiration sessions and masterclasses, as well as by carrying out small-scale AI projects that are tailored in close consultation with regional entrepreneurs and offered at an attractive rate. MKB Datalab-Oost also offers students a Data Buddy programme, in which students assess the opportunities within a company for getting started with an AI project.
The initiative is a collaboration between Radboud University and the University of Twente. It invites entrepreneurs in the eastern part of the Netherlands to learn more about AI and the opportunities it can offer them. The projects are carried out by AI and Data Science students from Radboud University, who are supported by lecturers.
