Universal Prediction of Individual Sequences

Meir Feder, Neri Merhav, Michael Gutman

Research output: Contribution to journalArticlepeer-review


The problem of predicting the next outcome of an individual binary sequence using finite memory, is considered. The finite-state predictability of an infinite sequence is defined as the minimum fraction of prediction errors that can be made by any finite-state (FS) predictor. It is proved that this FS predictability can be attained by universal sequential prediction schemes. Specifically, an efficient prediction procedure based on the incremental parsing procedure of the Lempel-Ziv data compression algorithm is shown to achieve asymptotically the FS predictability. Finally, some relations between compressibility and predictability are pointed out, and the predictability is proposed as an additional measure of the complexity of a sequence. nite-state machines, Lempel-Ziv algorithm.

Original languageEnglish
Pages (from-to)1258-1270
Number of pages13
JournalIEEE Transactions on Information Theory
Issue number4
StatePublished - Jul 1992


  • Predictability
  • complexity
  • compressibility
  • fi-


Dive into the research topics of 'Universal Prediction of Individual Sequences'. Together they form a unique fingerprint.

Cite this