Time Series Rule Discovery: Tough, Not Meaningless

  • Zbigniew R. Struzik
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2871)

Abstract

‘Model free’ rule discovery from data has recently been subject to considerable criticism, which has cast a shadow over the emerging discipline of time series data mining. However, other than in data mining, rule discovery has long been the subject of research in statistical physics of complex phenomena. Drawing from the expertise acquired therein, we suggest explanations for the two mechanisms of the apparent ‘meaninglessness’ of rule recovery in the reference data mining approach.

One reflects the universal property of self-affinity of signals from real life complex phenomena. It further expands on the issue of scaling invariance and fractal geometry, explaining that for ideal scale invariant (fractal) signals, rule discovery requires more than just comparing two parts of the signal. Authentic rule discovery is likely to look for the possible ‘structure’ pertinent to the failure mechanism of the (position and/or resolution-wise) invariance of the time series analysed.

The other reflects the redundancy of the ‘trivial’ matches, which effectively smoothes out the rule which potentially could be discovered. Orthogonal scale space representations and appropriate redundancy suppression measures over autocorrelation operations performed during the matches are suggested as the methods of choice for rule discovery.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Lin, J., Keogh, E., Truppel, W.: When is Time Series Clustering Meaningful? In: preprint Workshop on Clustering High Dimensional Data and its Applications, SDM (2003), will appear on the workshop site: www.cs.utexas.edu/users/inderjit/sdm03.html
  2. 2.
    Das, G., Lin, K., Mannila, H., Renganathan, G., Smyth, P.: Rule Discovery from Time Series. In: Proceedings of the 4th Intl. Conference on Knowledge Discovery and Data Mining, New York, NY, August 27-31, pp. 16–22 (1998)Google Scholar
  3. 3.
    Mantegna, R.N., Stanley, H.E.: An Introduction to Econophysics: Correlations and Complexity in Finance Cambridge. Cambridge University Press, England (2000)Google Scholar
  4. 4.
    Arneodo, A., Muzy, J.F., Sornette, D.: Eur. Phys J. B 2, 277 (1998), http://xxx.lanl.gov/ps/cond-mat/9708012
  5. 5.
    Johansen, A., Sornette, D.: Stock Market Crashes are Outliers. Eur. Phys. J. B 1, 141–143 (1998); Johansen, A., Sornette, D.: Large Stock Market Price Drawdowns Are Outliers arXiv:cond-mat/0010050 (October 3, 2000) rev. July 25, 2001Google Scholar
  6. 6.
    Podobnik, B., Ivanov, P.C., Lee, Y., Stanley, H.E.: Scale-invariant Truncated Lévy Process. Europhysics Letters 52, 491–497 (2000)CrossRefGoogle Scholar
  7. 7.
    Struzik, Z.R.: Wavelet Methods in (Financial) Time-series Processing. Physica A: Statistical Mechanics and its Applications 296(1-2), 307–319 (2001)MATHCrossRefMathSciNetGoogle Scholar
  8. 8.
    Sornette, D., Malevergne, Y., Muzy, J.F.: Volatility Fingerprints of Large Shocks: Endogeneous Versus Exogeneous, arXiv:cond-mat/0204626 (2002)Google Scholar
  9. 9.
    Struzik, Z.R.: Revealing Local Variablity Properties of Human Heartbeat Intervals with the Local Effective Hölder Exponent. Fractals 9(1), 77–93 (2001)CrossRefMathSciNetGoogle Scholar
  10. 10.
    Jaffard, S.: Multifractal Formalism for Functions: I. Results Valid for all Functions, II. Self-Similar Functions. SIAM J. Math. Anal. 28(4), 944–998 (1997)MATHCrossRefMathSciNetGoogle Scholar
  11. 11.
    Daubechies, I.: Ten Lectures on Wavelets. S.I.A.M. (1992) Google Scholar
  12. 12.
    Holschneider, M.: Wavelets – An Analysis Tool. Oxford Science Publications (1995)Google Scholar
  13. 13.
    Mallat, S.G., Hwang, W.L.: Singularity Detection and Processing with Wavelets. IEEE Trans. on Information Theory 38, 617 (1992); Mallat, S.G., Zhong, S.: Complete Signal Representation with Multiscale Edges. IEEE Trans. PAMI 14, 710 (1992)Google Scholar
  14. 14.
    Mallat, S., Zhang, Z.: Matching Pursuit in a Time-frequency Dictionary. IEEE Transactions on Signal Processing 41, 3397–3415 (1993)MATHCrossRefGoogle Scholar
  15. 15.
    Coifmann, R.R., Wickerhauser, M.V.: Entropy-based Algorithm for Best-basis Selection. IEEE Transactions on Information Theory 38, 713–718 (1992)CrossRefGoogle Scholar
  16. 16.
    Sweldens, W.: The Lifting Scheme: Construction of Second Generation Wavelets. SIAM J. Math. Anal. 29(2), 511–546 (1997)CrossRefMathSciNetGoogle Scholar
  17. 17.
    Muñoz Barrutia, A., Ertlé, R., Unser, M.: Continuous Wavelet Transform with Arbitrary Scales and O(N) Complexity. Signal Processing 82(5), 749–757 (2002)CrossRefGoogle Scholar
  18. 18.
    Unser, M., Aldroubi, A., Schiff, S.J.: Fast Implementation of the Continuous Wavelet Transform with Integer Scales. IEEE Transactions on Signal Processing 42(12), 3519–3523 (1994)CrossRefGoogle Scholar
  19. 19.
    Struzik, Z.R.: Oversampling the Haar Wavelet Transform. Technical Report INSR0102, CWI, Amsterdam, The Netherlands (March 2001)Google Scholar
  20. 20.
    Arneodo, A., Bacry, E., Muzy, J.F.: Oscillating Singularities in Locally Self-Similar Functions. PRL 74(24), 4823–4826 (1995)CrossRefGoogle Scholar
  21. 21.
    Arneodo, A., Bacry, E., Muzy, J.F.: The Thermodynamics of Fractals Revisited with Wavelets. Physica A 213, 232 (1995); Muzy, J.F., Bacry, E., Arneodo, A.:The Multifractal Formalism Revisited with Wavelets. Int. J. of Bifurcation and Chaos 4(2), 245 (1994)Google Scholar
  22. 22.
    Yang, A.C.-C., Hseu, S.-S., Yien, H.-W., Goldberger, A.L., Peng, C.-K.: Linguistic Analysis of the Human Heartbeat using Frequency and Rank Order Statistics. PRL (2003) (in press)Google Scholar
  23. 23.
    Struzik, Z.R.: Taming Surprises. In: Proceedings of the New Trends in Intelligent Information Processing and Web Mining conference, Zakopane, June 2–5 (2003)Google Scholar
  24. 24.
    Falconer, K.: Fractal Geometry: Mathematical Foundations and Applications. John Wiley, Chichester (1990) (paperback 1997)Google Scholar
  25. 25.
    Arneodo, A., Bacry, E., Muzy, J.F.: Wavelets and Multifractal Formalism for Singular Signals: Application to Turbulence Data. PRL 67(25), 3515–3518 (1991)CrossRefGoogle Scholar
  26. 26.
    Stanley, H.E., Meakin, P.: Multifractal Phenomena in Physics and Chemistry. Nature 335, 405–409 (1988)CrossRefGoogle Scholar
  27. 27.
    Ivanov, P.C., Rosenblum, M.G., Nunesv Amaral, L.A., Struzik, Z.R., Havlin, S., Goldberger, A.L., Stanley, H.E.: Multifractality in Human Heartbeat Dynamics. Nature 399, 461–465 (1999)CrossRefGoogle Scholar
  28. 28.
    Bunde, A., Kropp, J., Schellnhuber, H.J. (eds.): The Science of Disasters, Climate Disruptions, Heart Attacks, and Market Crashes. Springer, Heidelberg (2002)Google Scholar
  29. 29.
    Arneodo, A., Bacry, E., Muzy, J.F.: Solving the Inverse Fractal Problem from Wavelet Analysis. Europhysics Letters 25(7), 479–484 (1994)CrossRefGoogle Scholar
  30. 30.
    Arneodo, A., Argoul, A., Muzy, J.F., Tabard, M., Bacry, E.: Beyond Classical Multifractal Analysis using Wavelets: Uncovering a Multiplicative Process Hidden in the Geometrical Complexity of Diffusion Limited Aggregates. Fractals 1, 629 (1995)CrossRefMathSciNetGoogle Scholar
  31. 31.
    Struzik, Z.R.: The Wavelet Transform in the Solution to the Inverse Fractal Problem. Fractals 3(2), 329 (1995)MATHCrossRefGoogle Scholar
  32. 32.
    Struzik, Z.R., Siebes, A.P.J.M.: Wavelet Transform in Similarity Paradigm. In: Wu, X., Kotagiri, R., Korb, K.B. (eds.) PAKDD 1998. LNCS, vol. 1394, pp. 295–309. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  33. 33.
    Smola, A., Schölkopf, B.: A Tutorial on Support Vector Regression, NeuroCOLT2 technical report NC-TR-1998-030 (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Zbigniew R. Struzik
    • 1
  1. 1.Centrum voor Wiskunde en Informatica (CWI)AmsterdamThe Netherlands

Personalised recommendations