Master thesis Map Matching and Most Probable Path Prediction (f/m/x)

BMW M Motorsport / BMW Group; München; Vor Ort; EUR 40.000 - 70.000; Vollzeit

Zusammenfassung

Join BMW Group as a Machine Learning Intern where you'll explore innovative ways to process geolocation data and improve predictive models. You will have the opportunity to work extensively with data and develop essential skills through comprehensive mentoring. This full-time internship lasts 6 months starting from November 2025.

Leistungen

Comprehensive mentoring & onboarding

Personal & professional development

Flexible working hours

Digital offers & mobile working

Attractive & fair remuneration

Apartment offers for students in Munich

Qualifikationen

• Solid foundation in machine learning and data analysis.
• Experience with supervised and reinforcement learning techniques.
• Familiarity with symbolic reasoning and graph theory.

Aufgaben

• Employ rule-based reasoner to calculate the Most Probable Path.
• Implement supervised learning ML model.
• Conduct comparative analysis of machine learning approaches.

Kenntnisse

Machine Learning

Data Analysis

Problem Solving

Analytical Skills

Ausbildung

Studies in computer science, data science, or related field

Tools

Python

Jobbeschreibung

At BMW Group, you will explore a data-driven approach that combines symbolic reasoning and machine learning techniques to effectively match noisy geolocation data and compute the car’s Most Probable Path (MPP), utilizing real-world data represented as an RDF knowledge graph.

What awaits you?

• You employ a rule-based reasoner utilizing map data represented as an RDF knowledge graph to accurately calculate the Most Probable Path (MPP).
• Here, you implement a supervised learning machine learning model to directly predict the MPP based on observed data and road networks, often eliminating the need for hand-crafted rules or extensive domain knowledge.
• Additionally, you utilize a reinforcement learning ML model to train an agent for calculating the MPP.
• You apply suitable machine learning models, such as sequence-to-sequence or transformer-based architectures, to map GPS trajectories onto a digital map represented as a knowledge graph.
• Furthermore, you conduct a comparative analysis of the results, drawing conclusions about the advantages and disadvantages of each approach to inform future developments.

Please note that your thesis must be supervised by a university on your part.

What should you bring along?

• Studies in computer science, data science, or a related field.
• A solid foundation in machine learning and data analysis.
• Proficiency in programming languages such as Python, along with experience in machine learning libraries and frameworks.
• Familiarity with symbolic reasoning, graph theory, and neural network architectures, particularly in the context of Graph Neural Networks and knowledge graphs.
• Experience with supervised and reinforcement learning techniques, as well as an understanding of graph embedding methods.
• Strong analytical and problem-solving skills, enabling you to tackle complex challenges.

Do you have an enthusiasm for new technologies and an innovative environment? Apply now!

What do we offer?

• Comprehensive mentoring & onboarding.
• Personal & professional development.
• Flexible working hours.
• Digital offers & mobile working.
• Attractive & fair remuneration.
• Apartment offers for students (subject to availability & only Munich).
• And many other benefits - seejobs/benefits

Earliest starting date: 08/11/2025

Duration:6 months

Working hours:Full-time

Do you have any questions? Then simply send your enquiry using ourcontact form. Your enquiry will then be answered by telephone or e-mail.

At the BMW Group, we place great importance on equal treatment and equal opportunities. Our recruiting decisions are based on the personality, experience, and skills of the applicants.

Learn morehere.