1. The Penn-Lehman Automated Trading Project Michael Kearns Computer and Information Science University of Pennsylvania PLAT development team: Luis Ortiz, Berk Kapicioglu, Byoungjoon Kim, Rashid Tuweiq

2. What Is It? A project in real-time, automated trading in financial markets A realistic, multi-client market simulator using live and historical depth-of-market data A competitive testbed for trading strategies An investigation of order book strategies An investigation of AI & ML methods for automated trading A research and educational partnership between Penn and Lehman Brothers

3. Market Microstructure and Depth-of-Market Consider an exchange for some specific security (e.g. MSFT stock) Market order: specify number of shares desired, but leave price to “the market” Limit order: specify number of shares and desired price (usually away from the market) Limit orders are placed in a queue (or “book”) on the buy or sell side, ordered by price Market orders are matched with the top of the book on the opposing side, giving price Market orders “guaranteed” transaction but not price; limit orders guaranteed price but not transaction

4. Electronic Crossing Networks (ECNs) Matching process as old as financial markets Previously done manually (NYSE specialists) Electronic Crossing Networks (ECNs): –Automate matching process –Now publishing order book data –Can be highly liquid Examples: Island (17% of NASDAQ volume), Instinet, Archipelago,… Consolidation efforts (SuperMontage) OUCH and ITCH messaging protocols Example: island.htm or http://www.island.com/island.htmhttp://www.island.com/

5. The Penn Exchange Simulator (PXS) A (conceptually) simple, real-time market simulator exploiting order book data Core processes: –Data Gathering: frequent (live or historical) polling of any given stock from www.island.comwww.island.com –Client Order Processing: acceptance of connections and limit orders from automated clients via API –Market Simulation: simulation of matching process in a virtual market merging the Island and client data; computation of profit and loss of clients

6. LAST MATCH Pric e 23.7790 Time 9:01:55.61 4 TODAY'S ACTIVITY Orders1,630 Volume44,839 BUY ORDERS SHA RES PRICE 1,00 0 23.760 0 3,08 7 23.750 0 200 23.750 0 100 23.740 0 1,72 0 23.728 0 2,00 0 23.720 0 1,00 0 23.700 0 100 23.700 0 100 23.700 0 800 23.697 0 500 23.650 0 3,00 0 23.650 0 4,30 0 23.650 0 2,00 0 23.650 0 200 23.620 0 (195 more) SELL ORDERS SHA RES PRICE 100 23.780 0 800 23.799 0 500 23.800 0 1,72 0 23.807 0 900 23.819 0 200 23.850 0 1,00 0 23.850 0 1,00 0 23.850 0 1,00 0 23.860 0 200 24.000 0 500 24.000 0 1,00 0 24.030 0 200 24.030 0 1,10 0 24.040 0 500 24.050 0 (219 more) Client 1 Client 2 Client 3 BUYSELL V 23.80 V 23.77 I 23.76 I 23.75 V 23.74 I 23.74 V 23.74 V 23.73 I 23.73 I 23.78 I 23.80 V 23.80 I 23.81 V 23.82 V 23.83 V 23.84 I 23.85 I 23.86 V 23.89 V 23.90 V 23.97 V 24.00 PXS early-snap.txt later-snap.txt pxsAPI9.htm

7. Features of PXS Simulation merges real market data with client No guesses or models for limit order fills Permits investigation of order-book strategies Permits high-speed, high volume trading Forces real-time performance Sandbox for diverse strategies & interaction Execute “live” on real-time data or historical

8. Design Challenges Data volume, network latency, performance Timing issues in live versus historical Partial observability of Island queues Client impact on market Future functionality: –Multi-stock simulation –External data feeds –Web interface and GUI –Multiple ECNs; other markets (futures, options)

9. The Project: Participants Penn Development Team: –PXS design, development, maintenance –Client strategy design –Education of student researchers/users –Competition design and execution Students: –Approximately 30 students designing 13 strategies –Many senior projects; many joint CIS-Wharton –Several external participants (UTexas and CMU) Lehman: –Financial support from proprietary trading –Student mentorship and competition judging

10. Goals for the Trading Strategies and Competitions Attempt to recreate Wall Street “biodiversity” Market making, pairs trading, VWAP, block trading, technical strategies, etc. Investigate predictive value of order book data Investigate application of AI and ML methods Create a library of strategies and competition structures for mix and match experimentation

11. Strategy Types Many order-book strategies: –order book imbalance and variations obi.gif or Island Individual Investorsobi.gifIsland Individual Investors Market-making strategies Traditional technical strategies: –various “breakout” strategies, trend spotting, etc. –often with order-book modulation Machine learning strategies using order books –boosting –case-based learning –SVMs

12. The Competitions All have share position limits Fall 2002 Historical MSFT Competition hist2002.html Fall 2002 Live MSFT Competition (1-day) LiveComp.htm red-smooth250.ps blue-smooth250.ps Order-book Face-off obonly.html Currently: 3-round, 3-week MSFT Competition FebComp.htm FebComp.htm

13. Further Info General: www.cis.upenn.edu/~mkearns/www.cis.upenn.edu/~mkearns/ PLAT: www.cis.upenn.edu/~mkearns/projects/pat.htmlwww.cis.upenn.edu/~mkearns/projects/pat.html mkearns@cis.upenn.edu New participants welcome!