Talk Abstract: The architecture of modern E-commerce companies typically revolves around micro-services, this often causes a challenge for Data Scientists who need to pull data from disparate sources to carry out their day to day work. This pushes the typical 80% of time spent on data exploration, closer to 100%, resulting in less time spent solving the customer problem. At Trainline, we have solved this using event sourcing and streaming technology. We will talk about how this is practically carried out from a data engineering to data product development perspective. We will then explore advancing this technology, giving the ability to put realtime data products into production and the hands of our customers.
Bio: Sam is the Lead Machine Learning Engineer in the Data Science team at Trainline. He has worked on many of the customer facing data products at Trainline from Price Prediction to BusyBot and recommendation engines. He enjoys deploying data products at scale that positively impact the lives of Trainline’s customers. Previously he has worked in fintech and telecoms, working with machine learning to optimise the customer experience.