Traffic jams and over-crowded public transport is a problem that is highly researched in the mobility domain. Many companies are eager to predict it and would like to have these kinds of predictions at their disposal. There is no clear-cut solution to it… yet. We invite you to think outside of the box and determine other promising avenues from problem to solution!
- Machine learning
- Data Visualisation, Collection, Cleaning
- Feature extraction
- Explainable AI
- Random Forest
- Topic modelling
- Sentiment Analysis
What do you get
- A challenging assignment within a practical environment
- € 1000 compensation, € 500 + lease car or € 600 + living space
- Professional guidance
- Courses aimed at your graduation period
- Support from our academic Research center at your disposal
- Two vacation days per month
What you will do
- 65% Research
- 10% Analyze, design, realize
- 25% Documentation
The Dutch are champions in organizing events of all shapes and sizes. More than a thousand festivals per year, countless sport matches and concerts, large conventions in dedicated venues and well-organized demonstrations when there is something to protest about. For every organized event, people that do not live close by need to commute, either via public transport or by car.
To prevent traffic jams and over-crowded public transport, it would be extremely useful to be able to accurately predict beforehand which parts of the Dutch infrastructure should expect an influx in commuters, so that the necessary measurements can be taken to prevent over-crowdedness, for example by scheduling more buses or opening extra lanes on the highway.
You will be working on a solution to this problem that uses Twitter data, enriched with data from other sources, to accurately predict which locations in the Netherlands will see an influx in visitors within the next couple of days, so that ample measures can be taken to prevent this over-crowdedness.
To solve this highly-researched problem, you will need to collect tweets and use Natural Language Processing techniques like Topic Modelling and Sentiment Analysis to determine the upcoming events that generate buzz, in order to predict large gatherings based on twitter traffic about that particular event. Because twitter data alone will not contain enough information to predict crowdedness on the Dutch roads and stations, you will need to enrich it by using all the data you can get your hands on, like weather data in order to see if the weather has effect on people’s travelling movement, and information about Dutch national holidays to verify whether having the day off influences the amount of travelers to a certain location.
Furthermore, you will need to match events to the location where they take place by getting information from the Events section on Facebook or any of the other websites that can be used to find events in your area.
You will also need test data, which could be gathered by collecting information about past traffic jams or visitors for past events in order to get labels that can be used to train and test a number of different Machine Learning models.
This graduation assignment will allow you to work on a real-life use case, and you will be able to use state-of-the-art techniques in order to help solve this highly-researched problem. You will also be able to work on a challenging project in its entirety, by studying past publications, collecting and cleaning data, designing and training models, interpreting the results and visualizing the predictions on a map of the Netherlands. You will be guided by the best Data and AI experts that work at Info Support, but you will also have the freedom to approach this problem differently than described above in order to achieve the highest chance of success. This is the kind of problem for which an accurate solution could have far-reaching consequences for a large number of our customers in the Mobility and Public domain, and we are challenging you to find this solution!
About Info Support Research Center
We anticipate on upcoming and future challenges and ensures our engineers develop cutting-edge solutions based on the latest scientific insights. Our research community proactively tackles emerging technologies. We do this in cooperation with renowned scientists, making sure that research teams are positioned and embedded throughout our organisation and our community, so that their insights are directly applied to our business. We truly believe in sharing knowledge, so we want to do this without any restrictions.
Read more about Info Support Research here.