Building a machine learning GUI for the Office of Rail and Road
The Office of Rail and Road (ORR) is the British national rail regulator, responsible for health and safety on mainline rail, the London Underground, light rail, and trams.
ORR has a large amount of structured data feeds in a standardised format of Location, Date, and Value, recording train performance, weather, maintenance costs, trespasses, and other incidents. There is a further large data lake of unstructured text data.
The engineers and analysts at ORR are often tasked with constructing causal analyses such as
- a trespasser was able to get on the track
- because high winds had damaged fencing
- because maintenance on barriers had been cut in that region,
but an obstacle to these kinds of analysis is the difficulty of linking together disparate and differently structured data sets.
The ORR set out a need for a graphical user interface which would allow non-technical stakeholders to explore patterns and relationships within the organisation’s data, beyond what would be possible with the standard Power BI set-up.
We developed an in-browser tool that allows users to explore datasets graphically and link them together, building machine learning models which are able to predict effects such as flood-related delays as a function of flooding and money spent on drainage. We have also enabled users to harness natural language processing (NLP) to find key phrases and topics which are common in given areas of the country or at certain dates.
Our GUI was a first in ORR as it has allowed high-ranking stakeholders to experiment with machine learning using a simple and easy-to-understand graphical interface, and has enabled ORR to develop ideas about the future potential of machine learning in rail regulation.