NYC Python Meetup Algorithmic Trading talk (extended slides)

Transcript

1. Algorithmic Trading in Python Thomas Wiecki @twiecki
2. About me
3. About me
4. Rise of the machines 84% of all stock trades are done by computers
5. Rise of the machines 84% of all stock trades are done by computers vs
6. Rise of the machines 84% of all stock trades are done by computers vs Rationality Speed Capacity Intuition Understanding - Cognitively biased / emotional - Human - Limited + 50 years of experience + Knows how the market works + Purely analytical + 1 TFLOP + Big Data - None - Depends on programming
7. Rise of the machines 84% of all stock trades are done by computers vs Rationality Speed Capacity Intuition Understanding Speech - Cognitively biased / emotional - Human - Limited + 50 years of experience + Knows how the market works + Native speaker + Purely analytical + 1 TFLOP + Big Data - None - Depends on programming - “I'll be back”
8. Pythonic Algorithmic Trading Pipeline Data Analysis Generate ideas Tools: • Pandas • Matplotlib • (Seaborn) • IPython Backtesting Test on historical data whether idea can be exploited. Tools: • Zipline • Quantopian • PyAlgoTrader Forward testing Paper-trade on real-time market data. Tools: • Quantopian Live trading Trade with real money. Tools: • Quantopian (soon) optimize
9. Pythonic Algorithmic Trading Pipeline Data Analysis Generate ideas Tools: • Pandas • Matplotlib • (Seaborn) • IPython
10. Pythonic Algorithmic Trading Pipeline Data Analysis Generate ideas Tools: • Pandas • Matplotlib • (Seaborn) • IPython Backtesting Test on historical data whether idea can be exploited. Tools: • Zipline • Quantopian • PyAlgoTrader optimize
11. Pythonic Algorithmic Trading Pipeline Data Analysis Generate ideas Tools: • Pandas • Matplotlib • (Seaborn) • IPython Backtesting Test on historical data whether idea can be exploited. Tools: • Zipline • Quantopian • PyAlgoTrader Forward testing Paper-trade on real-time market data. Tools: • Quantopian optimize
12. Pythonic Algorithmic Trading Pipeline Data Analysis Generate ideas Tools: • Pandas • Matplotlib • (Seaborn) • IPython Backtesting Test on historical data whether idea can be exploited. Tools: • Zipline • Quantopian • PyAlgoTrader Forward testing Paper-trade on real-time market data. Tools: • Quantopian Live trading Trade with real money. Tools: • Quantopian (soon) optimize
13. Algorithmic Trading: Backtesting Historical stock data • datetime • Price • Volume Trading Algorithm • Applies transforms (e.g. mavg) • Makes trading decision • Places orders • Transaction costs • Slippage • Order delay Performance and Risk analysis
14. Zipline • Trading simulator/backtester written in Python • Open-Source (Apache 2.0) • Stream-based (prevents look-ahead bias) • Batteries included – Moving average, Sharpe, alpha, beta... • Used in production on Quantopian.com – Contribute back to community – Linus' law: "given enough eyeballs, all bugs are shallow" • http://zipline.io
15. Interoperability
16. Architecture Source Moving Average VWAP Regression User Algorithm Transaction Simulator Transform layer places orders executes orders Emits price and volume info
17. Go to: http://bit.ly/1cx0Gj7
18. Conclusions • Zipline gives you full control over you backtest. • Copy & paste your Zipline algorithm to Quantopian: – Share it, get feedback. – Test it on minute data. – Forward test it. – Go live (soon!)
19. Come hack Wall Street. Questions? @twiecki @quantopian