Pro Active for Algorithmic Trading NEHAL PATEL GMO

Algorithmic Trading at GMO What we do: Introduction to our business High-level grid/distributed computing

What we do Our Business: Invest money for clients Methodology: “Algorithmic Trading” Computers Math

Current Environment Trades Currencies and futures on 24 hour, continuous basis ~4000 trades a

Motivation Basic Problem: How can you make money using computers for investing? Basic Wisdom

Methodology Mathematics Machine Learning/Data mining (Like Biotech, Web) Dynamic Programming (Like Airline Scheduling) Computer

Algorithmic Trading at GMO What we do: Introduction to our business High-level computing goals

Distributed Computing Tasks Real-time Stochastic Control Complex Event Processing Real Time Statistical Analysis Data

Distributed Computing Goals Style Distributed Objects living in a sea of multicast data Lightweight

Algorithmic Trading at GMO What we do: Introduction to our business High-level distributed computing

Attractive Features POJOS Separation of Concerns High Speed simulation Toolset Focus Rapid Deployment Dynamic

Pro. Active Consulting with Active. Eon Low Level Architecture Topics: Performance More Transparency for

Slides: 12

Download presentation

Pro. Active for Algorithmic Trading NEHAL PATEL GMO OCTOBER 21, 2008

Algorithmic Trading at GMO What we do: Introduction to our business High-level grid/distributed computing goals Pro. Active

What we do Our Business: Invest money for clients Methodology: “Algorithmic Trading” Computers Math (some ) Finance Our Team: 12 members based in Boston and Minsk Educational background: Math, Physics, Computer Science Work Experience: Finance, Academics, Biotech, Internet startups

Current Environment Trades Currencies and futures on 24 hour, continuous basis ~4000 trades a day, $10 billion, 9 banks Two data centers, ~200 nodes, dozens processes

Motivation Basic Problem: How can you make money using computers for investing? Basic Wisdom Trade frequently, but smartly /Law of Large Numbers Ideas last for months not years Agility, Creativity Find the right edge Math and CS are equally important Embrace complexity, don’t sacrifice robustness

Methodology Mathematics Machine Learning/Data mining (Like Biotech, Web) Dynamic Programming (Like Airline Scheduling) Computer Science Java (~750, 000 lines) Emphasis on infrastructure Utilize open source Data Sets: 4 -5 Terabytes Real-time, Event processing: ~30 K messages/s

Algorithmic Trading at GMO What we do: Introduction to our business High-level computing goals Pro. Active

Distributed Computing Tasks Real-time Stochastic Control Complex Event Processing Real Time Statistical Analysis Data Mining Large Datasets Batch Processing Historical Simulation

Distributed Computing Goals Style Distributed Objects living in a sea of multicast data Lightweight Agile Features Scalability P 2 P / Data Push-Pull Same Code both simulation and production

Algorithmic Trading at GMO What we do: Introduction to our business High-level distributed computing goals Pro. Active

Attractive Features POJOS Separation of Concerns High Speed simulation Toolset Focus Rapid Deployment Dynamic byte code

Pro. Active Consulting with Active. Eon Low Level Architecture Topics: Performance More Transparency for POJOs