Time series analysis for sport data
In this project the goal is to explore existing state of the art methods from machine learning and statistics such as Recurrent neural networks, ARMA and Long short term memory networks. After getting a good overview of existing methods the next step in the project would be to work on improvements of existing methods with a focus on possibilities of combining statistical methods with machine learning ones to improve one or the other.
As a use case we provide a large and realistic dataset from a sport scenario containing measurements and self reports from professional athletes over a long period of time.
This project has several possible sub projects which can be decided based on the students. Some examples are:
- Comparison of existing statistical and machine learning based methods
- Measurement of performance and evaluation metrics improvement
- Improvement of current methods
- Combining statistical methods with machine learning based methods, etc.
- Insight into advanced techniques of machine learning
- Working on a real world application
- Collaboration with researchers in the topic of machine learning
- Possibility to implement and research a novel approach
- Pål Halvorsen
- Michael Riegler
- Hugo Lewi Hammer, OsloMet, email@example.com