Mathematical Finance & Financial Data Science Seminar
Machine Learning for Trading
Speaker: Gordon Ritter, Courant Institute of Mathematical Sciences
Location: Warren Weaver Hall 109
Date: Friday, April 26, 2019, 5:30 p.m.
In multi-period trading with realistic market impact, determining the dynamic trading strategy that optimizes expected utility of final wealth is a hard problem. In this paper we show that, with an appropriate choice of the reward function, reinforcement learning techniques (specifically, Q-learning) can successfully handle the risk-averse case. We provide a proof of concept in the form of a simulated market which permits a statistical arbitrage even with trading costs. The Q-learning agent finds and exploits this arbitrage
Bio – Gordon Ritter
Adjunct professor at Courant Institute of Mathematical Sciences, New York University
Buy-Side Quant of the Year Award in 2019
Gordon Ritter completed his PhD in mathematical physics at Harvard University in 2007, where he published in top international journals across the fields of quantum computation, quantum field theory, and abstract algebra. Prior to that he earned his Bachelor's degree with honors in Mathematics from the University of Chicago, completing many graduate courses while still an undergraduate. Gordon is currently a senior portfolio manager and leader of a team trading a broad range of market-neutral absolute return strategies across geographies and asset classes. Gordon is also responsible for directing all research in GSA's New York office. GSA has won the Equity Market Neutral & Quantitative Strategies category at the Eurohedge awards four times, with numerous other awards. Prior to joining GSA, Gordon was a Vice President of Highbridge Capital Management and a core member of the firm's statistical arbitrage group. Concurrently with his positions in industry, Gordon teaches at three of the nation's leading MFE programs, including Baruch College and NYU (both ranked in the top 5 MFE programs). He has published several articles on portfolio optimization in Risk, the most widely-read practitioner journal, and is frequently invited to speak at the top industry conferences, such as Risk USA and Global Derivatives. Gordon received the Buy-Side Quant of the Year Award in 2019.