* News


Teaching Machines to Read for Fun and Profit

Speaker: Gary Kazantssev
Bloomgberg R&D

February 25, 2014 - 4:00 p.m. to 5:00 p.m.
Location: CII (Low) 3051
Hosted By: Dr. Malik Magdon-Ismail (x4857)


Gary Kazantsev, manager of the Machine Learning group at Bloomberg, will talk about a challenging learning problem: predicting price impact of news stories. We begin with an overview of the current and upcoming projects in Machine Learning and NLP at Bloomberg and then focus on our Machine Learning approach to the following question, "Does news move prices of financial instruments?" We describe work investigating this question empirically, with the intent of building predictive models of market behavior. Our research is driven by the objective of producing predictive models of equity prices based on text of financial news stories (and ultimately other factors). This problem is challenging in several different aspects due to the nature of the models required: the work is at the intersection of text analysis using supervised learning and financial time series modeling via regression analysis and semi-supervised anomaly detection.


Gary Kazantsev runs the R&D Machine Learning group at Bloomberg LP, leading projects in the areas of computational linguistics and machine learning such as sentiment analysis, market impact indicators, text classification, social media analytics, question answering, recommenda-tion systems and predictive modeling of financial markets. He holds degrees in physics, mathematics and computer science from Boston University.

Last updated: February 13, 2014