Ben Chamberlain – Lead Data Scientist, ASOS

Ben Chamberlain leads the data science team at managing a broad range of e-commerce projects across four data science divisions. He held a Royal Commission for the Exhibition of 1851 Industrial Fellowship, which funded his PhD in statistical machine learning at Imperial College London. His research focuses on learning and representation of large graphs and applications to social network and e-commerce sites. Ben has ten years of industry experience and has previously worked as a data scientist working with social networks and in the UK defence and security industries. He is a physics graduate of the University of Oxford. Outside of work, Ben plays rugby in London for Hackney RFC and he’s hoping that someone will let him play for their team in the Tech Tag Tournament – he’s bringing his boots


This talk will cover how neural network embeddings can be used to improve marketing and recommendations in e-commerce. It includes a non-mathematical introduction to embeddings, a discussion of the applications in e-commerce, some real-world problems in applying them at scale. If there’s time, it will finish with some future extensions and research directions.

Embeddings are one of the most successful applications of neural networks. They first shot to prominence in Word2vec, a model for distributed representations of words developed at Google by Tomas Mikolov et al. They are a key part of all voice recognition systems (Siri, Alexa etc.), modern search engines and seem to improve any imaginable NLP task. Recently, embeddings have been applied in a broad array of domains including to represent social media users (eg. Facebook’s social graph), Amazon products and ASOS customers.