Whilst recommender systems are regularly found in the context of digital marketing and campaign selections, these powerful algorithms have the flexibility to be applied to a wide range of business problems. At Royal Mail we have used a hybrid recommendation system to better target our B2B marketing communications and are currently exploring the possibility of using recommenders to aid decision making by a wide range of colleagues. In this interview, Kat covers the challenges of moving recommenders away from the traditional spaces they occupy and discusses the power of combining business knowledge and recommendation algorithms to enable data-driven decision making in an operational setting.
• Tell us a bit more about your work at Royal Mail
• How did you begin your work in AI and more specifically in recommender systems?
• How are you using recommender systems at Royal Mail?
• What challenges are you currently facing in your work, and how is deep learning helping you solve them?
• What are AI’s implications for the retail industry as a whole?
• Which other industries are you most excited so see implementing AI for a positive impact in the next 5 years?
Kat James received her PhD from the University of Oxford in Statistical Genomics and completed a short Post Doc in Kumamoto, Japan working on the statistical challenges presented by whole blood RNASeq sampling in HIV-2 infected patients. Following on from roles at British Airways building solutions to destination recommendation problems and at Aviva, applying NLP techniques to customer complaints data, she is currently a Senior Data Scientist at Royal Mail, working on a variety of Data Science applications around optimisation, IoT devices, marketing and data-driven decision making. Current interests include recommender systems, AI, IoT and NLP.