Factor graphs for universal portfolios

Andrew J. Bean; Andrew C. Singer

doi:10.1109/ACSSC.2009.5469881

Factor graphs for universal portfolios

Andrew J. Bean
, Andrew C. Singer

Office of the Dean of the College of Engineering and Applied Sciences

University of Illinois at Urbana-Champaign

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Scopus citations

Abstract

We consider the sequential portfolio investment problem. Building on results in signal processing, machine learning, and other areas, we combine the insights of Cover and Ordentlich's side information portfolio with those of Blum and Kalai's transaction costs algorithm to construct one that performs well under transaction costs while taking advantage of side information. We introduce factor graphs as a computational tool for analysis and design of universal (low regret) algorithms, and develop our algorithm with this insight. Finally, we demonstrate that, in contrast to other algorithms, our portfolio performs well over the full range of costs.

Original language	English
Title of host publication	Conference Record - 43rd Asilomar Conference on Signals, Systems and Computers
Pages	1375-1379
Number of pages	5
DOIs	https://doi.org/10.1109/ACSSC.2009.5469881
State	Published - 2009
Event	43rd Asilomar Conference on Signals, Systems and Computers - Pacific Grove, CA, United States Duration: Nov 1 2009 → Nov 4 2009

Publication series

Name	Conference Record - Asilomar Conference on Signals, Systems and Computers
ISSN (Print)	1058-6393

Conference

Conference	43rd Asilomar Conference on Signals, Systems and Computers
Country/Territory	United States
City	Pacific Grove, CA
Period	11/1/09 → 11/4/09

Keywords

Factor graph
Investment
Piecewise models
Portfolio
Sum-product
Transaction costs
Universal

Access to Document

10.1109/ACSSC.2009.5469881

Cite this

@inproceedings{a8d310e0517647218e5b9435cadc061e,

title = "Factor graphs for universal portfolios",

abstract = "We consider the sequential portfolio investment problem. Building on results in signal processing, machine learning, and other areas, we combine the insights of Cover and Ordentlich's side information portfolio with those of Blum and Kalai's transaction costs algorithm to construct one that performs well under transaction costs while taking advantage of side information. We introduce factor graphs as a computational tool for analysis and design of universal (low regret) algorithms, and develop our algorithm with this insight. Finally, we demonstrate that, in contrast to other algorithms, our portfolio performs well over the full range of costs.",

keywords = "Factor graph, Investment, Piecewise models, Portfolio, Sum-product, Transaction costs, Universal",

author = "Bean, \{Andrew J.\} and Singer, \{Andrew C.\}",

year = "2009",

doi = "10.1109/ACSSC.2009.5469881",

language = "English",

isbn = "9781424458271",

series = "Conference Record - Asilomar Conference on Signals, Systems and Computers",

pages = "1375--1379",

booktitle = "Conference Record - 43rd Asilomar Conference on Signals, Systems and Computers",

note = "43rd Asilomar Conference on Signals, Systems and Computers ; Conference date: 01-11-2009 Through 04-11-2009",

}

Bean, AJ & Singer, AC 2009, Factor graphs for universal portfolios. in Conference Record - 43rd Asilomar Conference on Signals, Systems and Computers., 5469881, Conference Record - Asilomar Conference on Signals, Systems and Computers, pp. 1375-1379, 43rd Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, United States, 11/1/09. https://doi.org/10.1109/ACSSC.2009.5469881

TY - GEN

T1 - Factor graphs for universal portfolios

AU - Bean, Andrew J.

AU - Singer, Andrew C.

PY - 2009

Y1 - 2009

N2 - We consider the sequential portfolio investment problem. Building on results in signal processing, machine learning, and other areas, we combine the insights of Cover and Ordentlich's side information portfolio with those of Blum and Kalai's transaction costs algorithm to construct one that performs well under transaction costs while taking advantage of side information. We introduce factor graphs as a computational tool for analysis and design of universal (low regret) algorithms, and develop our algorithm with this insight. Finally, we demonstrate that, in contrast to other algorithms, our portfolio performs well over the full range of costs.

AB - We consider the sequential portfolio investment problem. Building on results in signal processing, machine learning, and other areas, we combine the insights of Cover and Ordentlich's side information portfolio with those of Blum and Kalai's transaction costs algorithm to construct one that performs well under transaction costs while taking advantage of side information. We introduce factor graphs as a computational tool for analysis and design of universal (low regret) algorithms, and develop our algorithm with this insight. Finally, we demonstrate that, in contrast to other algorithms, our portfolio performs well over the full range of costs.

KW - Factor graph

KW - Investment

KW - Piecewise models

KW - Portfolio

KW - Sum-product

KW - Transaction costs

KW - Universal

UR - https://www.scopus.com/pages/publications/77953837480

U2 - 10.1109/ACSSC.2009.5469881

DO - 10.1109/ACSSC.2009.5469881

M3 - Conference contribution

AN - SCOPUS:77953837480

SN - 9781424458271

T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers

SP - 1375

EP - 1379

BT - Conference Record - 43rd Asilomar Conference on Signals, Systems and Computers

T2 - 43rd Asilomar Conference on Signals, Systems and Computers

Y2 - 1 November 2009 through 4 November 2009

ER -

Factor graphs for universal portfolios

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this