I work for Findmypast transforming digitised historical documents into high quality genealogical resources. This involves structured and un-structured data, web-scraping, 3rd party APIs, special data protection requirements, machine learning models, and pipeline automation.
This is a personal project I started to collect and analyse various football related data.
For the last year or so I have volunteered with this AI For Good community project. It's aim is to combat climate misinformation, greenwashing and climate-related fake news. I have contributed to the project's Data Science code repository.
In 2019-20 I completed Udacity's Data Science Nanodegree.
- Blog on my analysis of 2019 Stackoverflow survey
- ML pipeline for disaster respose
- Image classification capstone