Nonlinear manifold learning for early warnings in financial markets

A financial market is a complex, dynamic system with an underlying governing manifold. This study introduces an early warning method for financial markets based on manifold learning. First, we restructure the phase space of a financial system using financial time series data. Then, we propose an information metric-based manifold learning (IMML) algorithm to extract the intrinsic manifold of a dynamic financial system. Early warning ranges for critical transitions of financial markets can be detected from the underlying manifold. We deduce the intrinsic geometric properties of the manifold to detect impending crises. Experimental results show that our IMML algorithm accurately describes the attractor manifold of the financial dynamic system, and contributes to inform investors about the state of financial markets.

[1]  Chris Papageorgiou,et al.  Did Established Early Warning Signals Predict the 2008 Crises , 2016 .

[2]  Péter Gács,et al.  Information Distance , 1998, IEEE Trans. Inf. Theory.

[3]  Alfred O. Hero,et al.  Information-Geometric Dimensionality Reduction , 2011, IEEE Signal Processing Magazine.

[4]  G. Seber.  Multivariate observations / G.A.F. Seber , 1983 .

[5]  L. Cao.  Practical method for determining the minimum embedding dimension of a scalar time series , 1997 .

[6]  Li Yang,et al.  Alignment of Overlapping Locally Scaled Patches for Multidimensional Scaling and Dimensionality Reduction , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Erkam Güresen,et al.  Developing an early warning system to predict currency crises , 2014, Eur. J. Oper. Res..

[8]  Simon van Norden,et al.  Regime Switching in Stock Market Returns , 1997 .

[9]  George Sugihara,et al.  Detecting Causality in Complex Ecosystems , 2012, Science.

[10]  S. Carpenter,et al.  Early-warning signals for critical transitions , 2009, Nature.

[11]  Hongyuan Zha,et al.  Principal Manifolds and Nonlinear Dimension Reduction via Local Tangent Space Alignment , 2002, ArXiv.

[12]  Stephen R. Carpenter,et al.  Early Warnings of Regime Shift When the Ecosystem Structure Is Unknown , 2012, PloS one.

[13]  T. Rydén,et al.  Stylized Facts of Daily Return Series and the Hidden Markov Model , 1998 .

[14]  M. Lang,et al.  The early warnings of banking crises: Interaction of broad liquidity and demand deposits , 2016 .

[15]  Yongbin Liu,et al.  Time-Frequency Manifold as a Signature for Machine Health Diagnosis , 2012, IEEE Transactions on Instrumentation and Measurement.

[16]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[17]  David S. Broomhead,et al.  Geometric Manifold Learning , 2011, IEEE Signal Processing Magazine.

[18]  A. Rényi.  On the dimension and entropy of probability distributions , 1959 .

[19]  Richard J. Povinelli,et al.  Time series classification using Gaussian mixture models of reconstructed phase spaces , 2004, IEEE Transactions on Knowledge and Data Engineering.

[20]  Gang Kou,et al.  Enhancing data consistency in decision matrix: Adapting Hadamard model to mitigate judgment contradiction , 2014, Eur. J. Oper. Res..

[21]  Davide Faranda,et al.  Early warnings indicators of financial crises via auto regressive moving average models , 2015, Commun. Nonlinear Sci. Numer. Simul..

[22]  María Concepción Ausín,et al.  A semiparametric Bayesian approach to the analysis of financial time series with applications to value at risk estimation , 2014, Eur. J. Oper. Res..

[23]  T. Moon.  The expectation-maximization algorithm , 1996, IEEE Signal Process. Mag..

[24]  A. Kolmogorov.  Three approaches to the quantitative definition of information , 1968 .

[25]  H. Boche,et al.  The Kullback–Leibler Divergence and Nonnegative Matrices , 2006, IEEE Transactions on Information Theory.

[26]  Christopher J. Rozell,et al.  Stable Takens' Embeddings for Linear Dynamical Systems , 2010, IEEE Transactions on Signal Processing.

[27]  Misako Takayasu,et al.  Econophysics approaches to large-scale business data and financial crisis : proceedings of the Tokyo Tech-Hitotsubashi Interdisciplinary Conference + APFA7 , 2010 .

[28]  Yi Peng,et al.  Evaluation of clustering algorithms for financial risk analysis using MCDM methods , 2014, Inf. Sci..

[29]  Y. Wong,et al.  Differentiable Manifolds , 2009 .

[30]  Anil K. Jain,et al.  Unsupervised Learning of Finite Mixture Models , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[31]  Gang Kou,et al.  A cosine maximization method for the priority vector derivation in AHP , 2014, Eur. J. Oper. Res..

[32]  H. Broer.  Dynamical systems and turbulence, Warwick 1980 , 1981 .

[33]  Antonio Artés-Rodríguez,et al.  Information-Theoretic Linear Feature Extraction Based on Kernel Density Estimators: A Review , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[34]  Robert Jenssen,et al.  Kernel Entropy Component Analysis , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[35]  Gang Kou,et al.  A kernel entropy manifold learning approach for financial data analysis , 2014, Decis. Support Syst..

[36]  A. Timmermann,et al.  Regime Changes and Financial Markets , 2011 .

[37]  S. Carpenter,et al.  Anticipating Critical Transitions , 2012, Science.

[38]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[39]  Oleg Bondarenko,et al.  Assessing Measures of Order Flow Toxicity and Early Warning Signals for Market Turbulence , 2014 .

[40]  Hongbin Zha,et al.  Riemannian Manifold Learning , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[41]  H. Zha,et al.  Principal manifolds and nonlinear dimensionality reduction via tangent space alignment , 2004, SIAM J. Sci. Comput..

[42]  Thomas H. McCurdy,et al.  How Useful are Historical Data for Forecasting the Long-Run Equity Return Distribution? , 2007 .

[43]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[44]  I. Hasan,et al.  Financial Crises and Bank Failures: A Review of Prediction Methods , 2009 .

[45]  José G. Dias,et al.  Mining categorical sequences from data using a hybrid clustering method , 2014, Eur. J. Oper. Res..

[46]  M. Scheffer,et al.  Complexity theory and financial regulation , 2016, Science.

[47]  H. Sebastian Seung,et al.  The Manifold Ways of Perception , 2000, Science.