There is a lot of data available about the use of the ISIS facility and how this fits with the wider UK science funding environment and academic publications, but the data is messy, noisy and difficult to compare.
The project would involve discovering the available open data sources/APIs for this information, creating links between these different datasets using deterministic and probabilistic methods, and using data science tools to explore and analyse the data to discover links and patterns. There will be the opportunity to investigate a range of tools including simple machine learning approaches. The role will require the use and development of APIs and databases using programming languages, as well as the use of data exploration and interactive visualization tools
Over the course of the post you will gain real world experience in areas such as:
- Software development in a professional environment
- Gain a real-world understanding of open data APIs and formats
- Data exploration skills including interactive visualization