Creating Community Through Graph Embeddings: Machine Learning at WeWork

3:30 - 4:00 | Thursday, May 23

Embeddings have become a popular set of methods for representing discrete entities as continuous vectors. These vectors can then be used as features for standard machine learning tasks such as classification or clustering. Advances in the literature have extended the original text embedding framework to accommodate new types of data such as images, genetic sequences, and song playlists. Of particular interest is a recently introduced method called “node2vec” that learns embeddings for nodes in a network, using a novel random-walk based sampling scheme on top of a skip-gram architecture. This algorithm is an especially pertinent use case for our team, since WeWork’s member community can conveniently be expressed in graphical form. In this talk, we’ll discuss how we construct networks and use “node2vec” to create rich feature representations of WeWork communities, and then build recommendation services that are powered by these trained models. In particular, we focus on member-to-member recommendations as well as other data products that facilitate the creation of real-life connections.

Karry Lu
Sr. Data Scientist, WeWork

Karry Lu is a senior data scientist at WeWork with degrees in economics and statistics, and interests in recommendation systems, NLP, and Bayesian inference. In previous lives, he has led machine learning at a (successfully exited!) foodtech startup, and fought crime for the feds with the power of linear regression. Even more previous lives include relapsed statistician, community organizer and failed novelist.