Machine Learning in Trading
Systematic trading strategies have a long and turbulent history, from Richard Donchian's simple trend-timing to modern tools like TA-Lib and OLMAR. Yet despite all the sophistication of quantitative finance, many production trading strategies today are still based on some combination of: trend following, mean reversion, value/yield and growth (as noted by Rishi Narang).
This event is entirely devoted to understanding how modern machine learning methods can be applied to the development of systematic trading strategies. We will have hands-on workshops of the Quantopian stack (Zipline and Pyfolio), as well as talks by leading practitioners from industry and academia.
May 12, 2016, 9:00a - 6:00p
140 New Montgomery
San Francisco, CA 94105
Registration & Breakfast
Gary Kazantsev, Bloomberg Manager R&D Machine Learning.
Steven Pav. Guarding Against Broken Backtests and Questionable Research in Quantitative Strategies
Arshak Navruzyan, Startup.ML. Machine Learning Based Bitcoin Trading.
Justin Lent, Quantopian. Zipline and Pyfolio Workshop.
Shota Ishii, State Street GX. Data-Driven Approach to Multi-asset Class Portfolio Risk Estimation
Matthew Dixon, IIT. Classification-based Market Prediction using Deep Neural Networks
Bringing machine learning to industry and startups by training the next generation of data scientists. Our fellowship program gives new data scientists the chance to hone their skills by building real-world, scalable machine learning systems.
Bloomberg builds the technology that quickly and accurately delivers business and financial information, news and insight around the world.