I now have a finalised research direction for my PhD. I’m going to be working in anomaly detection as a sub-field of statistical applied mathematics. My supervisors are Idris Eckley and Paul Fearnhead.
What this means is I’m looking at ways to deal with datasets that are complicated and messy, and to identify data points that are complicated and messy in a different way to the main bit of the data. In particular, my project is sponsored by BT, and some of the problems they’d like me to solve are about flagging up issues in the telecommunications network they need to go out and fix. These show up as strange blips in overall network usage over time against a backdrop of ‘normal’ human behaviour (which can itself be very strange, from the point of view of an algorithm).
Anomaly detection is used in many places and almost everywhere lots of data is processed, answering questions like “is this transaction fraudulent?” or “do we need to switch off this expensive piece of machinery and do a maintenance check?” or “is there a planet orbiting this star?”. It’s a really nice field to work in in terms of being driven by real-world applications but also not tied directly to any one real-world application, keeping open lots of future opportunities about who you work with and what you work on.
The setup of the research group, StatScale, that I have become a part of at Lancaster (which, believe it or not, is a collaboration with Cambridge – I never can seem to get away from that place!) is also really welcoming, friendly, and full of bright people who get on well together. More details about it can be found at https://www.statscale.org/.