# Real-Time Signalextraction (MDFA) and Algorithmic Trading - PowerPoint PPT Presentation

Real-Time Signalextraction (MDFA) and Algorithmic Trading

1 / 79
Real-Time Signalextraction (MDFA) and Algorithmic Trading

## Real-Time Signalextraction (MDFA) and Algorithmic Trading

- - - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - - -
##### Presentation Transcript

1. Real-Time Signalextraction (MDFA) and Algorithmic Trading marc.wildi@zhaw.ch http://blog.zhaw.ch/idp/sefblog http://www.idp.zhaw.ch/usri http://www.idp.zhaw.ch/MDFA-XT http://www.idp.zhaw.ch/sef

2. Background • Hybrid math/econ. • IDP-ZHAW → Projects with econ. partners • Forecasting • Health-care (cost expenditures) • Macro (real-time economic indicators: EURI Eurostat-project) • Finance (MDFA-XT, large hedge-fund) • Engineering (Telecom, load forecasts) • Eclectic/disparate range of applications • Common methodological approach(es) • In-house developments: (M)DFA • R-package “signalextraction” on CRAN

3. A Classical Algorithmic Trading Approach Timing System SP500 Daily Closures MA(200), Equally Weighted

4. P.5 (drawdowns), p.7 (timing system), p.10 (performance)

5. Problem: (Too) Long Periods with Systematic Underperformance

7. Log-MSCI and MA(45)

8. Filter Characteristics • Amplitude function: • Which signal is extracted? • Time-shift: • How large is the delay?

9. Timing System (MSCI-Weekly)

10. Conclusions • Crossing-rules are (an unnecessarily cumbersome way of implementing)bandpass filters • Crossing-rules (bandpass) have small time delays • Why MDFA? • Flexible efficient real-time (bandpass) design • Fast and smooth

11. Fundamental Trading http://www.idp.zhaw.ch/usri SP500 http://blog.zhaw.ch/idp/sefblog

12. USRI (MDFA) and SP500

13. Performance in Logs

14. Student Thesis p.19 Long Term Performances Fundam. Trading

15. Conclusion • Damp or avoid all massive recession draw-downs effectively • Ideal for risk-averse investors (pension funds) • Fundamental Trading: truly out of sample • Focus on Macro-data (finance data ignored) • NBER • Disadvantage: `insufficiently active’ • Texto: «Difficult to justify fees»

16. MDFA-XT http://www.idp.zhaw.ch/MDFA-XT MSCI (+BRIC) http://blog.zhaw.ch/idp/sefblog

17. Log-MSCI and MA(45)

18. MDFA vs. MA(45) weekly dataMDFA (blue) Faster

20. Filter « Unfrequent »

21. Filter « Unfrequent to Mid»

22. Filter « Mid »

23. Filter « Frequent »

24. Conclusion • Higher trading frequencies are associated with • Bandpass shifted to the right • More flexible than traditional filter-crossings • Smaller delays/time shifts

25. Performances

26. Setting • Total degenerative trading costs of 0.3% per order (small fund) • Long only • No risk free interest rates

27. Performance « Unfrequent »

28. Performance « Unfrequent to Mid»

29. Performance « Mid»

30. Performance « Mid to Frequent »

31. Performance « Frequent »

32. Conclusions • Higher trading frequencies are associated with • Slight reduction of performance • Larger draw-downs • USRI would avoid draw-downs and then the performance would improve • Increased market activity (fees!) • Combination with USRI possible (recommended) • Filters will be available on-line in late July

33. Real-Time Signalextraction A SEF-Blog Excel-Tutorial http://blog.zhaw.ch/idp/sefblog

34. Excel-Tutorial on SEF-Blog • http://blog.zhaw.ch/idp/sefblog/index.php?/archives/65-Real-Time-Detection-of-Turning-Points-a-Tutorial-Part-I-Mean-Square-Error-Norm.html • http://blog.zhaw.ch/idp/sefblog/index.php?/archives/67-Real-Time-Detection-of-Turning-Points-a-Tutorial-Part-II-Emphasizing-Turning-Points.html

35. Purposes • Yoga exercises to detach from main-stream maximum likelihood world • First Blog-entry: how traditional econometric approach `works’ • Intuitively straightforward • Good (optimal) mean-square performances • People have become lazy-minded • Second Blog-Entry: the early detection of turning points • Is a (strongly) counterintuitive exercise • Generates seemingly (strongly) misspecified filter designs • Warning → Learning (→ Illumination?)

36. Excel-Tutorial on SEF-Blog

37. Real-Time Signalextraction 1. Traditional Econometrics

39. Standard Econometric Approach • Proceeding: • Identify a time-series model (ARIMA/state space) • Extend the series by optimal forecasts • Apply the symmetric filter on the extended time series • X-12-ARIMA, TRAMO, STAMP, R/S+… • Claim: • One-sided filter is optimal (mean-square sense) • Assumption: DGP/true model

40. ARMA(2,2)-Diagnostics

41. Real-Time Model-Based Filter

42. Real-Time Signalextraction 2. Excel Example (Replication of Model-Based Approach)

43. Parameters (ARMA(2,2)-FILTER) • ARMA(2,2)-Filter (not model)

44. A Seemingly Virtuous Design (amplitude)

45. A Seemingly Virtuous Design (time shift)

46. A Seemingly Virtuous Design(Peak Correlation) • Correlation between real-time estimate and cycle as a function of time-lag k

47. Signal and Estimate(Estimate: Filter Tweaked by Hand)

48. Real-Time Signalextraction 3. Excel Example (Turning Point Revelation)

49. Parameters ARMA(2,2)-FILTERSeemingly Misspecified Design • ARMA(2,2)-Filter (not model)