Universal portfolios with side information


We present a sequential investment algorithm, the-weighted universal portfolio with side-information, which a c hieves, to rst order in the exponent, the same wealth as the best side-information dependent i n v estment strategy the best state-constant re-balanced portfolio determined in hindsight from observed market and side-information outcomes. This is an individual sequence result which shows that the diierence between the exponential growth rates of wealth of the best state-constant rebalanced portfolio and the universal portfolio with side-information is uniformly less than d=2n logn + 1 + k=n log 2 for every stock market and side-information sequence and for all time n. Here d = km , 1 is the number of degrees of freedom in the state-constant rebal-anced portfolio with k states of side-information and m stocks. The proof of this result establishes a close connection between universal investment and universal data compression.

DOI: 10.1109/18.485708

Extracted Key Phrases

Showing 1-10 of 17 references

Notes from lecture on universal data compression delivered at Stanford University

  • Csisz Ar
  • 1993

Universal schemes for prediction, gambling, and portfolio selection

  • P H Algoet
  • 1992

Empirical Bayes stock market portfolios

  • M Cover, D Gluss
  • 1986

Growth Optimal Trading Strategies

  • D C Larson
  • 1986

Information Theory: Coding Theorems for Discrete Memoryless Systems

  • J Csisz Ar, Kk Orner
  • 1981

The performance of universal encoding

  • R E Krichevsky, V K Troomov
  • 1981
Showing 1-10 of 143 extracted citations


Citations per Year

227 Citations

Semantic Scholar estimates that this publication has received between 176 and 298 citations based on the available data.

See our FAQ for additional information.