Master Thesis: Strategies for Missing ML Data Labels
Ericsson ABSammanfattning
This opportunity involves a master's thesis project focused on building cell coverage models using machine learning techniques to handle missing signal strength measurements in mobile networks. The work will utilize data collected by Ericsson from a real radio access network and will culminate in a presentation of results to the Ericsson development team. The position is based in Linköping, Sweden.Det här erbjuder vi
Opportunity to work with real operational network data.Collaboration with a diverse team of innovators.Chance to contribute to solutions for complex problems in mobile networks.
Ansök senast: Öppet tillsvidare
Publicerad: 2026-10-11
Beskrivning
Join our Team
About this opportunity:
As mobile networks are becoming increasingly complex, one way of increasing performance and making the mobile network more self-autonomous is to apply machine learning techniques. For example, machine learning can be used to predict signal strength for certain frequencies or cells given a position in the radio environment. Such prediction models rely on signal strength measurements carried out by real devices, where measurements may be imperfect or biased in different ways, causing bad predictions.
A central challenge in building such models from operational network data is that a substantial fraction of measurements may be missing, either because the true signal falls below the hardware detection limit, a left-censoring mechanism, or because of transient reporting failures unrelated to signal strength.
An earlier master thesis evaluated modelling strategies for frequency coverage models. The work in this thesis will focus on building cell coverage models instead, as well as refining the evaluation strategies for missing labels. The data set will consist of measurements already collected by Ericsson from a real radio access network.
What you will do:
The skills you bring:
Why join Ericsson?
At Ericsson, you'll have an outstanding opportunity. The chance to use your skills and imagination to push the boundaries of what's possible. To build solutions never seen before to some of the world's toughest problems. You'll be challenged, but you won't be alone. You'll be joining a team of diverse innovators, all driven to go beyond the status quo to craft what comes next.
What happens once you apply?
Click Here to find all you need to know about what our typical hiring process looks like.Encouraging a diverse and inclusive organization is core to our values at Ericsson, that's why we champion it in everything we do. We truly believe that by collaborating with people with different experiences we drive innovation, which is essential for our future growth. We encourage people from all backgrounds to apply and realize their full potential as part of our Ericsson team. Ericsson is proud to be an Equal Opportunity Employer. learn more.
Primary country and city: Sweden (SE) || Linköping
Req ID: 792030
About this opportunity:
As mobile networks are becoming increasingly complex, one way of increasing performance and making the mobile network more self-autonomous is to apply machine learning techniques. For example, machine learning can be used to predict signal strength for certain frequencies or cells given a position in the radio environment. Such prediction models rely on signal strength measurements carried out by real devices, where measurements may be imperfect or biased in different ways, causing bad predictions.
A central challenge in building such models from operational network data is that a substantial fraction of measurements may be missing, either because the true signal falls below the hardware detection limit, a left-censoring mechanism, or because of transient reporting failures unrelated to signal strength.
An earlier master thesis evaluated modelling strategies for frequency coverage models. The work in this thesis will focus on building cell coverage models instead, as well as refining the evaluation strategies for missing labels. The data set will consist of measurements already collected by Ericsson from a real radio access network.
What you will do:
- Investigate and compare different techniques for handling missing labels for cell coverage models.
- Apply a selection of techniques to evaluate their performance.
- The thesis will be concluded with a result presentation for the Ericsson development team.
The skills you bring:
- Master's student in computer science, computer engineering or statistics and machine learning.
Why join Ericsson?
At Ericsson, you'll have an outstanding opportunity. The chance to use your skills and imagination to push the boundaries of what's possible. To build solutions never seen before to some of the world's toughest problems. You'll be challenged, but you won't be alone. You'll be joining a team of diverse innovators, all driven to go beyond the status quo to craft what comes next.
What happens once you apply?
Click Here to find all you need to know about what our typical hiring process looks like.Encouraging a diverse and inclusive organization is core to our values at Ericsson, that's why we champion it in everything we do. We truly believe that by collaborating with people with different experiences we drive innovation, which is essential for our future growth. We encourage people from all backgrounds to apply and realize their full potential as part of our Ericsson team. Ericsson is proud to be an Equal Opportunity Employer. learn more.
Primary country and city: Sweden (SE) || Linköping
Req ID: 792030
Ansök till tjänsten
Master Thesis: Strategies for Missing ML Data Labels
OM FÖRETAGET
Ericsson AB
