Wavelet transform based multifractal formalism in outlier detection and localisation for financial time series

We present a method of detecting and localising outliers in financial time series and other stochastic processes. The method checks the internal consistency of the scaling behaviour of the process within the paradigm of the multifractal spectrum. Deviation from the expected spectrum is interpreted as the potential presence of outliers. The detection part of the method is then supplemented by the localisation analysis part, using the local scaling properties of the time series. Localised outliers can then be removed one by one, with the possibility of dynamic verification of spectral properties. Both the multifractal spectrum formalism and the local scaling properties of the time series are implemented on the wavelet transform modulus maxima tree.

[1]  E. Bacry,et al.  Wavelet Analysis of Fractal Signals Application to Fully Developed Turbulence Data , 1993 .

[2]  Zbigniew R. Struzik.  Oversampling the Haar wavelet transform , 2001 .

[3]  Scaling transformation and probability distributions for financial time series , 1999, cond-mat/9905169.

[4]  F. Schmitt,et al.  Multifractal analysis of foreign exchange data , 1999 .

[5]  Zbigniew R. Struzik,et al.  Outlier detection and localisation with wavelet based multifractal formalism , 2000 .

[6]  Didier Sornette,et al.  Large Stock Market Price Drawdowns are Outliers , 2000, cond-mat/0010050.

[7]  E. Bacry,et al.  The Multifractal Formalism Revisited with Wavelets , 1994 .

[8]  Zbigniew R. Struzik.  Removing divergences in the negative moments of the multi-fractal partition function with the wavelet transformation , 1998 .

[9]  D. Sornette,et al.  Causal cascade in the stock market from the ``infrared'' to the ``ultraviolet'' , 1997, cond-mat/9708012.

[10]  E. Bacry,et al.  Wavelets and multifractal formalism for singular signals: Application to turbulence data. , 1991, Physical review letters.

[11]  E. Bacry,et al.  Characterizing long-range correlations in DNA sequences from wavelet analysis. , 1995, Physical review letters.

[12]  Zbigniew R. Struzik.  The Wavelet Transform in the Solution to the Inverse Fractal Problem , 1995 .

[13]  Stéphane Mallat,et al.  Singularity detection and processing with wavelets , 1992, IEEE Trans. Inf. Theory.

[14]  SOLVING THE TWO-DIMENSIONAL INVERSE FRACTAL PROBLEM WITH THE WAVELET TRANSFORM , 1996 .

[15]  Ingrid Daubechies,et al.  Ten Lectures on Wavelets , 1992 .

[16]  Emmanuel Bacry,et al.  THE THERMODYNAMICS OF FRACTALS REVISITED WITH WAVELETS , 1995 .

[17]  Shlomo Havlin,et al.  Scaling behaviour of heartbeat intervals obtained by wavelet-based time-series analysis , 1996, Nature.

[18]  Jacques Lévy Véhel,et al.  Fractals: Theory and Applications in Engineering , 1999 .

[19]  D. Sornette,et al.  ”Direct” causal cascade in the stock market , 1998 .

[20]  V S L'vov,et al.  Outliers, extreme events, and multiscaling. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[21]  E. Bacry,et al.  BEYOND CLASSICAL MULTIFRACTAL ANALYSIS USING WAVELETS: UNCOVERING A MULTIPLICATIVE PROCESS HIDDEN IN THE GEOMETRICAL COMPLEXITY OF DIFFUSION LIMITED AGGREGATES , 1993 .

[22]  E. Bacry,et al.  Solving the Inverse Fractal Problem from Wavelet Analysis , 1994 .

[23]  Zbigniew R. Struzik.  Local Effective Hölder Exponent Estimation on the Wavelet Transform Maxima Tree , 1999 .

[24]  Didier Sornette,et al.  Stock market crashes are outliers , 1998 .

[25]  Matthias Holschneider,et al.  Wavelets - an analysis tool , 1995, Oxford mathematical monographs.

[26]  Bacry,et al.  Oscillating singularities in locally self-similar functions. , 1995, Physical review letters.

[27]  Jacques Lévy Véhel,et al.  2-Microlocal Analysis and Application in Signal Processing , 1998 .

[28]  Y. Meyer,et al.  Wavelet Methods for Pointwise Regularity and Local Oscillations of Functions , 1996 .