Online annotation and prediction for regime switching data streams

Regime switching models, in which the state of the world is locally stationary, are a useful abstraction for many continuous valued data streams. In this paper we develop an online framework for the challenging problem of jointly predicting and annotating streaming data as it arrives. The framework consists of three sequential modules: prediction, change detection and regime annotation, each of which may be instantiated in a number of ways. We describe a specific realisation of this framework with the prediction module implemented using recursive least squares, and change detection implemented using CUSUM techniques. The annotation step involves associating a label with each regime, implemented here using a confidence interval approach. Experiments with simulated data show that this methodology can provide an annotation that is consistent with ground truth. Finally, the method is illustrated with foreign exchange data.

[1]  Ulrich Appel,et al.  Adaptive sequential segmentation of piecewise stationary time series , 1983, Inf. Sci..

[2]  S. Haykin,et al.  Adaptive Filter Theory , 1986 .

[3]  Terrence J. Sejnowski,et al.  Variational Learning for Switching State-Space Models , 2001 .

[4]  E. S. Page.  CONTINUOUS INSPECTION SCHEMES , 1954 .

[5]  Muni S. Srivastava.  Cusum procedure for monitoring variability , 1997 .

[6]  R. Quandt.  The Estimation of the Parameters of a Linear Regression System Obeying Two Separate Regimes , 1958 .

[7]  J. Durbin,et al.  Techniques for Testing the Constancy of Regression Relationships Over Time , 1975 .

[8]  Michèle Basseville,et al.  Detection of abrupt changes: theory and application , 1993 .

[9]  A. Goel,et al.  Determination of A.R.L. and a Contour Nomogram for Cusum Charts to Control Normal Mean , 1971 .

[10]  L. Rabiner,et al.  An introduction to hidden Markov models , 1986, IEEE ASSP Magazine.

[11]  F. Gustafsson.  The marginalized likelihood ratio test for detecting abrupt changes , 1996, IEEE Trans. Autom. Control..

[12]  Jean-Pierre Vila,et al.  Adaptive threshold computation for CUSUM-type procedures in change detection and isolation problems , 2008, Comput. Stat. Data Anal..

[13]  M.A. Carlin,et al.  Detection of Speaker Change Points in Conversational Speech , 2007, 2007 IEEE Aerospace Conference.

[14]  Elizabeth Ann Maharaj,et al.  Cluster of Time Series , 2000, J. Classif..

[15]  Andrew W. Moore,et al.  Learning to recognize time series: combining ARMA models with memory-based learning , 1997, Proceedings 1997 IEEE International Symposium on Computational Intelligence in Robotics and Automation CIRA'97. 'Towards New Computational Principles for Robotics and Automation'.

[16]  R. Khan,et al.  Sequential Tests of Statistical Hypotheses. , 1972 .

[17]  Marcella Corduas,et al.  Time series clustering and classification by the autoregressive metric , 2008, Comput. Stat. Data Anal..

[18]  Sven Knoth.  Computation of the ARL for CUSUM-S , 2006, Comput. Stat. Data Anal..

[19]  S. B. Needleman,et al.  A general method applicable to the search for similarities in the amino acid sequence of two proteins. , 1970, Journal of molecular biology.

[20]  Stephen Gray,et al.  Regime switching in foreign exchange rates : Evidence from currency option prices , 2000 .

[21]  Sridhar Mahadevan,et al.  Switching kalman filters for prediction and tracking in an adaptive meteorological sensing network , 2005, 2005 Second Annual IEEE Communications Society Conference on Sensor and Ad Hoc Communications and Networks, 2005. IEEE SECON 2005..