Bloomberg: Finding Signals in Tweets with ML/NLP at Bloomberg - Lunch Provided

Talk Abstract:

In the current social media era, Twitter has proven itself an indispensable source of information as we frequently see information posted or shared on Twitter become big market movers later on. Due to the mass volume, directly consuming the raw contents without any kind of refinements is undesirable, and, more importantly, the vast majority of the contents are irrelevant to what interests our clients. In this talk, we will discuss how to refine raw contents from Twitter and extract fruitful signals, e.g. Trending Topics, Company Sentiments, Social Velocity, etc from them. Furthermore, we will discuss challenges during developments of the business deliverables and how we solve them via the use of ML/NLP techniques. Finally, we will go over some applications which are built on top of these signals and used broadly by professionals in the finance domain.

Iat Chong Chan - Profile:

Iat Chong Chan is a software developer in Bloomberg Machine Learning Team. His interests mostly lie in the intersection of Computational Linguistics, Machine Learning, and High Performance Computing. He has been working on a scalable infrastructure to infer topics of social contents ingested to Bloomberg by statistical models, and also a set of tools to maintain and improve these classifiers. Iat Chong also leads the NLP guild inside Bloomberg, to advocate the use of ML/NLP techniques for new business problems. Before he joined the company, he was a MSc student in Dept. of Computer Science at University of Oxford, supervised by Prof. Stephen Pulman and Yishu Miao, and worked on building a better input method on small hand-held devices by a novel Bayesian Network with Variational Inference.

Free lunch will be provided!