Master Thesis: Applying Machine Learning in DevOps
Mobility is changing - and Veoneer is a part of driving this change towards safe mobility solutions.
You will have access to exciting and emerging technologies. We focus on your professional and technical growth within advanced driving assistance systems (ADAS) and collaborative driving. We empower our teams to move technology forward in this fast-paced and challenging industry.
Are you ready to contribute to this change? Veoneer has around 7,500 purpose-driven employees in 11 countries around the world - come join Veoneer as we lead the way in Creating Trust in Mobility.
Machine Learning, Computer Science
Machine learning can be trained to identify significant trends over time and help correlate datasets from e.g., server logs, applications, and monitoring tools. A well-chosen algorithm is expected to match actual faults, support issues and service outage.
Large amount of data is collected by monitoring tools in Veoneer DevOps environment in addition to the data generated from continuous integration systems. The large amount of data it becomes challenging to manually analyze the collected data or try to find trends in the entire dataset.
Therefore, the need for machine processing of large datasets, and comparing results from different machine learning techniques to create a prediction model which can predict fault early in time.
Identify and prepare datasets, analyze, and correlate data to find trends and anomalies using machine learning techniques. Evaluate different techniques to create a prediction model for a fault at a given point of time.
- Data collection
- Machine learning
Number of student(s): 1-2
Student background: Master of Science
Extent: 30 credits (Master)
Start: Spring 2022
Contact information: For more information about the Master Thesis, please contact Recruiting Manager, Oscar Gustavsson, email@example.com
Last application date: 2021-10-31, applications will be evaluated continuously.
Are you ready to Create Trust in Mobility?