My team aims at using machine learning algorithms to provide a better experience to our audiences, mainly through personalisation.
I work very closely with Data Engineer, Editorial and Product.
I’ve mostly been involved in building a recommender system for production use for one of the main BBC products. The Machine Learning algorithm used is hybrid (mix of collaborative filtering and content-based: Factorization Machines). The code is developed in Python, following a TDD approach. Google Cloud Platform tools are used to manage the resources and to store the data, Airflow for the automation, and Redis for serving. I've been involved in all of the steps: from the algorithm development, to the engine productionisation, but also in making sure that the recommendations are compliant with our editorial policies and company values.
I've also been working on few NLP side projects like topic modelling (LDA).