Master’s Thesis: Predicting Mobility from Cellular Network Data

eghed is looking for two master’s students from Chalmers University of Technology to work on a challenging applied research problem at the intersection of mathematical statistics, machine learning and large-scale data analysis.

The project

The thesis focuses on developing and improving algorithms for predicting trips and modes of transportation from cellular network data. The dataset is very large and consists of trip-specific observations – or pings – generated through interactions with mobile network towers.

Turning these sparse and noisy observations into reliable estimates of movement and transportation mode poses several interesting statistical and computational challenges.

You will investigate existing approaches and explore ways of improving them – or develop new algorithms altogether. Depending on the direction of the project, relevant methods may include Monte Carlo simulation, Markov models and theory, probabilistic modelling, sampling techniques and statistical inference.

The project combines mathematical modelling with hands-on algorithm development and experimentation on a large real-world dataset.

Who are we looking for?

The thesis is particularly suitable for students in Applied Mathematics, Mathematical Statistics, Complex Adaptive Systems, Data Science/AI, or a related programme at Chalmers.

We expect you to have:

• A strong foundation in probability and mathematical statistics
• Good Python programming skills
• An interest in probabilistic modelling, algorithms and data-driven problem solving
• The ability and curiosity to work with large, complex datasets

The thesis corresponds to 30 ECTS and is intended to be carried out by two students. Applications from pairs are strongly preferred.

About eghed

eghed is a specialist consultancy within Data, Machine Learning and AI. We work with technically demanding problems where advanced analytics, mathematical modelling and software engineering meet real-world applications.

As a thesis student, you will work closely with experienced consultants and get the opportunity to turn theoretical methods into algorithms that operate on real data at scale.

How to apply

Send your application to thesis@eghed.se.

Please include:

• Your CV
• A short letter introducing yourselves, your relevant background, why you are suitable for the project, and why you would like to work on it
• Your Ladok transcripts

Preferably, apply together with the person you intend to carry out the thesis with.

For questions about the project, contact peter.helgesson@eghed.se or magnus.rahm@eghed.se.