Master thesis: ML Model of network data traffic
Ericsson ABSammanfattning
Ericsson is offering a master thesis opportunity focused on developing global statistical models for live 5G mobile network data traffic. This role involves exploring supervised learning techniques to enhance network dimensioning methodologies, ultimately aiming to optimize capacity, performance, and cost. The position is based in Stockholm, Sweden, and provides a chance to contribute to significant cost savings for the company while tackling real-world challenges in 5G networks.Det här erbjuder vi
Opportunity to work on innovative solutions in a diverse team.Chance to contribute to significant cost savings for Ericsson.Engagement in real-world applications of machine learning.
Ansök senast: Öppet tillsvidare
Publicerad: 2026-09-24
Beskrivning
Join our Team
About this opportunity:
Join Ericsson for a master thesis focused on investigating and implementing global statistical models of live 5G mobile network data traffic. Your work will support the dimensioning of future hardware and software architectures, helping balance capacity, performance, and cost. Finding the right tradeoff has the potential to save Ericsson hundreds of millions of SEK annually and forms part of our continuous efforts to improve network dimensioning methodologies.
What you will do:
You will explore supervised learning approaches, including probabilistic classification and regression, for modeling millisecond-level network data traffic. Your work will cover algorithm selection and parameter tuning, data rebalancing for highly imbalanced datasets, class selection or clustering, feature selection and dimensionality reduction, synthetic data generation using SMOTE-like methods, and the selection of suitable model performance and evaluation metrics. You will also investigate how well models generalize across different geographical areas and address big-data implementation constraints related to processing and storage. The expected outcome is a report describing the selected processing pipeline and the reasoning behind it, together with an application for model generation and inference, including performance evaluation.
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) || Stockholm
Req ID: 791323
About this opportunity:
Join Ericsson for a master thesis focused on investigating and implementing global statistical models of live 5G mobile network data traffic. Your work will support the dimensioning of future hardware and software architectures, helping balance capacity, performance, and cost. Finding the right tradeoff has the potential to save Ericsson hundreds of millions of SEK annually and forms part of our continuous efforts to improve network dimensioning methodologies.
What you will do:
You will explore supervised learning approaches, including probabilistic classification and regression, for modeling millisecond-level network data traffic. Your work will cover algorithm selection and parameter tuning, data rebalancing for highly imbalanced datasets, class selection or clustering, feature selection and dimensionality reduction, synthetic data generation using SMOTE-like methods, and the selection of suitable model performance and evaluation metrics. You will also investigate how well models generalize across different geographical areas and address big-data implementation constraints related to processing and storage. The expected outcome is a report describing the selected processing pipeline and the reasoning behind it, together with an application for model generation and inference, including performance evaluation.
The skills you bring:
- Strong foundation in mathematics and supervised learning, including model selection, probabilistic classification, and probabilistic regression
- Familiarity with data rebalancing, class selection, feature selection and reduction, model evaluation, and model generalization
- Good at working with big-data processing and storage constraints
- Interest in applying machine learning to real-world 5G network challenges
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) || Stockholm
Req ID: 791323
Ansök till tjänsten
Master thesis: ML Model of network data traffic
OM FÖRETAGET
Ericsson AB
