de.mpg.escidoc.pubman.appbase.FacesBean
English
 
Help Guide Disclaimer Contact us Login
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Proceedings

Model-based clustering with Hidden Markov Models and its application to financial times series data

MPS-Authors
http://pubman.mpdl.mpg.de/cone/persons/resource/persons50523

Schliep,  Alexander
Dept. of Computational Molecular Biology (Head: Martin Vingron), Max Planck Institute for Molecular Genetics, Max Planck Society;

Locator
There are no locators available
Fulltext (public)

Schliep.pdf
(Any fulltext), 118KB

Supplementary Material (public)
There is no public supplementary material available
Citation

Knab, B., Schliep, A., Steckemetz, B., & Wichern, B. (2003). Model-based clustering with Hidden Markov Models and its application to financial times series data. Berlin [et al]: Springer.


Cite as: http://hdl.handle.net/11858/00-001M-0000-0010-8B24-5
Abstract
We have developed a method to partition a set of data into clusters by use of Hidden Markov Models. Given a number of clusters, each of which is represented by one Hidden Markov Model, an iterative procedure finds the combination of cluster models and an assignment of data points to cluster models which maximizes the joint likelihood of the clustering. To reflect the non-Markovian nature of some aspects of the data we also extend classical Hidden Markov Models to employ a non-homogeneous Markov chain, where the non-homogeneity is dependent not on the time of the observation but rather on a quantity derived from previous observations. We present the method, a proof of convergence for the training procedure and an evaluation of the method on simulated time-series data as well as on large data sets of financial time-series from the Public Saving and Loan Banks in Germany.