Assignment for candidates
This is a mandatory assignment for everyone applying for the Applied Science Internship. Please return your answers along with your application.
This assignment is exclusively for the Applied Science internship position. If you want to apply for the Operations Research internship, please solve the corresponding assignment.
- Overview
- Choosing the data
- Choosing the approach
- Working with the data
- Your background and Wolt
- Submitting the assignment
Thank you for applying for Wolt's 2025 Applied Science Internship! The idea is not to spend an extensive amount of time on this, but to show how you think and approach problems.
There are two parts in this assignment:
- first, you get to work on an assignment: pick a dataset, explore it and prepare a couple of models based on it, and present your findings to us
- secondly, we will also take a look at your academic and extracurricular interests.
So, there are two things we would like you to submit.
-
Present your answers in a reproducible way and in an open format. Make sure you include the code and your reasoning, too. It pays to have a proper idea of Wolt's product and business, so it might be a good idea to take a look at our blog or some of the recent articles around the web.
-
Prepare a concise presentation (up to 7 slides excl. title slide) about the task and the solution you came up with. Make sure to submit the presentation in a pdf format. The target audience for your presentation is a potential future peer Applied Scientist with relevant business knowledge, so we hope you prepare it accordingly.
Good communication of our work to others is a key component for success in this role. Hence, we will use this presentation to screen applications, and to decide which assignments will be reviewed in detail. So keep it concise and clearly explain to us what you’ve done in the assignment; spark our interest to look deeper.
The presentation should contain some context for the selected approach, relevant insights from the data, some justification of selected modeling approach, as well as discussion around results and potential next steps.
Don't worry we're not looking for a massive research poster! Just a clear presentation of what, why, and how did you do things in the assignment. We'll grade the presentation based on the Technical quality as well as Communication skills.
There are many ways to successfully complete this assignment. If you have a unique approach and the right set of skills, this will be your chance to set yourself apart and shine!
We have prepared two datasets for you. Feel free to choose which data you use based on your background and ambitions. You only need to choose one.
- Consider the flow of orders in the provided file as a process fluctuating in time.
- Consider the daily average of courier partners online in the provided file.
Armed with a dataset, come up with a modeling task that is relevant to Wolt. To give you an idea what we are looking for, the task might look something like these:
- How many orders are we going to get tomorrow? Or next week?
- Where will the orders be delivered in an hour?
- Based on past data, can we forecast the amount of courier partners that will go online the following day, week, 2 weeks, or even longer?
- …and so on!
The minimum requirement is that your approach will result in some kind of predictive model. Choose one modeling task (with possibly more than one models trained) that properly showcases your skills!
Produce interesting statistics and graphs about the dataset. Show the most important features and explain what you see.
Why did you choose the approach, what kind of benefits do you see in solving it? What kind of metrics can you use to evaluate how good the solution is?
Based on the approach you choose, produce a model suitable for the task. You should include the preparation work, feature engineering and your thought process in your answer.
Are you happy with the results? What kind of results would you expect to see, if this was deployed to production?
Make slight modifications to the model or take a completely different method to solve it. Compare your two solutions. Strengths, weaknesses? What should you consider when you compare different models? If you had more time and resources, what kind of development could be done to make the solution better?
After the practical work, let's discuss what you have learned and what your ambitions are. Write a bit about the problems you like to work with. Have you written your thesis or a larger piece of coursework about something that you would see beneficial for Wolt? If you already have work history, are there some things that you would like to try here? Based on your knowledge about us, are there some problems you would like to help us solve? Do you have some relevant, interesting minors or side projects? We are always interested in enthusiastic people with fresh ideas, and this could be the opportunity to put something you recently learned into use!
Bundle everything into a Zip archive and upload it to Google Drive, Dropbox or similar and include the link in the application. Remember to check permissions! If we cannot access the file, we cannot review your solution. Please don’t store your solution in a public GitHub repository or otherwise share it.
A good check before sending your task is to unzip the Zip archive into a new folder and check that building and running the project works, using the steps you define in readme.md. Forgotten dependencies and instructions can sometimes happen even to the best of us.