Power mapping and noise reduction for financial correlations

Per-Johan Andersson, Andreas Öberg, Thomas Guhr

Research output: Chapter in Book/Report/Conference proceedingPaper in conference proceedingResearchpeer-review

4 Citations (SciVal)


The spectral properties of financial correlation matrices can show features known from completely random matrices. A major reason is noise originating from the finite lengths of the financial time series used to compute the correlation matrix elements. In recent years, various methods have been proposed to reduce this noise, i.e. to clean the correlation matrices. This is of direct practical relevance for risk management in portfolio optimization. In this contribution, we discuss in detail the power mapping, a new shrinkage method. We show that the relevant parameter is, to a certain extent, self-determined. Due to the "chirality" and the normalization of the correlation matrix, the optimal shrinkage parameter is fixed. We apply the power mapping and the well-known filtering method, to market data and compare them by optimizing stock portfolios. We address the rle of constraints by excluding short selling in the optimization.
Original languageEnglish
Title of host publicationActa Physica Polonica, Series B
PublisherJagellonian University, Cracow, Poland
Publication statusPublished - 2005
EventConference on Applications of Random Matrices to Economy and Other Complex Systems - Cracow, Poland
Duration: 2005 May 252005 May 28

Publication series

ISSN (Print)0587-4254


ConferenceConference on Applications of Random Matrices to Economy and Other Complex Systems

Bibliographical note

The information about affiliations in this record was updated in December 2015.
The record was previously connected to the following departments: Mathematical Physics (Faculty of Technology) (011040002)

Subject classification (UKÄ)

  • Physical Sciences


  • Stock portfolios
  • Shrinkage method
  • Financial correlation matrices
  • Financial time series


Dive into the research topics of 'Power mapping and noise reduction for financial correlations'. Together they form a unique fingerprint.

Cite this