Prediction by compression

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

It is well known that text compression can be achieved by predicting the next symbol in the stream of text data based on the history seen up to the current symbol. The better the prediction the more skewed the conditional probability distribution of the next symbol and the shorter the codeword that needs to be assigned to represent this next symbol. What about the opposite direction? suppose we have a black box that can compress text stream. Can it be used to predict the next symbol in the stream? We introduce a novel criterion based on the length of the compressed data and use it to predict the next symbol. We examine empirically the prediction error rate and its dependency on some compression parameters.

Original languageEnglish
Title of host publicationProceedings of the 8th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2011
Pages282-288
Number of pages7
DOIs
StatePublished - 2011
Event8th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2011 - Innsbruck, Austria
Duration: 16 Feb 201118 Feb 2011

Publication series

NameProceedings of the 8th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2011

Conference

Conference8th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2011
Country/TerritoryAustria
CityInnsbruck
Period16/02/1118/02/11

Keywords

  • Data compression
  • Statistical prediction
  • Universal sequence prediction

Fingerprint

Dive into the research topics of 'Prediction by compression'. Together they form a unique fingerprint.

Cite this