Performance of evolving trading strategies with different discount factors

Research output: Chapter in Book/Report/Conference proceedingChapter

2 Citations (Scopus)

Abstract

We use an evolving prediction model based on the idea of minority games in which traders continuously evaluate a complete set of trading strategies with different memory lengths using the strategies' past performance, weighted by a discount factor, and choose the strategy with the best past performance. Based on the chosen trading strategy they determine their prediction of the movement of each individual asset for the following time period. We find empirically using stocks from the SP500 that our prediction model yields a success rate and trading return that is increasing the smaller the discount factor becomes. We hypothesize that this result is driven by the existence of complex patterns of returns that are constantly changing and thus cannot be captured by relying on long-lasting experiences or static trading strategies.
Original languageEnglish
Title of host publication2011 IEEE Congress of Evolutionary Computation, CEC 2011
Place of PublicationPiscataway, NJ
PublisherIEEE
Pages186-191
Number of pages6
ISBN (Electronic)978-1-4244-7835-4
ISBN (Print)978-1-4244-7834-7
DOIs
Publication statusPublished - Jun 2011
Event2011 IEEE Congress of Evolutionary Computation, CEC 2011, June 5, 2011 - June 8, 2011 - New Orleans, LA, USA United States
Duration: 1 Jun 2011 → …

Publication series

Name2011 IEEE Congress of Evolutionary Computation, CEC 2011
PublisherIEEE Computer Society

Conference

Conference2011 IEEE Congress of Evolutionary Computation, CEC 2011, June 5, 2011 - June 8, 2011
CountryUSA United States
CityNew Orleans, LA
Period1/06/11 → …

Fingerprint

Discount factor
Trading strategies
Prediction model
Minorities
Assets
Prediction
Traders

Cite this

Krause, A. (2011). Performance of evolving trading strategies with different discount factors. In 2011 IEEE Congress of Evolutionary Computation, CEC 2011 (pp. 186-191). [5949617] (2011 IEEE Congress of Evolutionary Computation, CEC 2011). Piscataway, NJ: IEEE. https://doi.org/10.1109/CEC.2011.5949617

Performance of evolving trading strategies with different discount factors. / Krause, Andreas.

2011 IEEE Congress of Evolutionary Computation, CEC 2011. Piscataway, NJ : IEEE, 2011. p. 186-191 5949617 (2011 IEEE Congress of Evolutionary Computation, CEC 2011).

Research output: Chapter in Book/Report/Conference proceedingChapter

Krause, A 2011, Performance of evolving trading strategies with different discount factors. in 2011 IEEE Congress of Evolutionary Computation, CEC 2011., 5949617, 2011 IEEE Congress of Evolutionary Computation, CEC 2011, IEEE, Piscataway, NJ, pp. 186-191, 2011 IEEE Congress of Evolutionary Computation, CEC 2011, June 5, 2011 - June 8, 2011, New Orleans, LA, USA United States, 1/06/11. https://doi.org/10.1109/CEC.2011.5949617
Krause A. Performance of evolving trading strategies with different discount factors. In 2011 IEEE Congress of Evolutionary Computation, CEC 2011. Piscataway, NJ: IEEE. 2011. p. 186-191. 5949617. (2011 IEEE Congress of Evolutionary Computation, CEC 2011). https://doi.org/10.1109/CEC.2011.5949617
Krause, Andreas. / Performance of evolving trading strategies with different discount factors. 2011 IEEE Congress of Evolutionary Computation, CEC 2011. Piscataway, NJ : IEEE, 2011. pp. 186-191 (2011 IEEE Congress of Evolutionary Computation, CEC 2011).
@inbook{c897e59cbb134835843851ead997877d,
title = "Performance of evolving trading strategies with different discount factors",
abstract = "We use an evolving prediction model based on the idea of minority games in which traders continuously evaluate a complete set of trading strategies with different memory lengths using the strategies' past performance, weighted by a discount factor, and choose the strategy with the best past performance. Based on the chosen trading strategy they determine their prediction of the movement of each individual asset for the following time period. We find empirically using stocks from the SP500 that our prediction model yields a success rate and trading return that is increasing the smaller the discount factor becomes. We hypothesize that this result is driven by the existence of complex patterns of returns that are constantly changing and thus cannot be captured by relying on long-lasting experiences or static trading strategies.",
author = "Andreas Krause",
year = "2011",
month = "6",
doi = "10.1109/CEC.2011.5949617",
language = "English",
isbn = "978-1-4244-7834-7",
series = "2011 IEEE Congress of Evolutionary Computation, CEC 2011",
publisher = "IEEE",
pages = "186--191",
booktitle = "2011 IEEE Congress of Evolutionary Computation, CEC 2011",
address = "USA United States",

}

TY - CHAP

T1 - Performance of evolving trading strategies with different discount factors

AU - Krause, Andreas

PY - 2011/6

Y1 - 2011/6

N2 - We use an evolving prediction model based on the idea of minority games in which traders continuously evaluate a complete set of trading strategies with different memory lengths using the strategies' past performance, weighted by a discount factor, and choose the strategy with the best past performance. Based on the chosen trading strategy they determine their prediction of the movement of each individual asset for the following time period. We find empirically using stocks from the SP500 that our prediction model yields a success rate and trading return that is increasing the smaller the discount factor becomes. We hypothesize that this result is driven by the existence of complex patterns of returns that are constantly changing and thus cannot be captured by relying on long-lasting experiences or static trading strategies.

AB - We use an evolving prediction model based on the idea of minority games in which traders continuously evaluate a complete set of trading strategies with different memory lengths using the strategies' past performance, weighted by a discount factor, and choose the strategy with the best past performance. Based on the chosen trading strategy they determine their prediction of the movement of each individual asset for the following time period. We find empirically using stocks from the SP500 that our prediction model yields a success rate and trading return that is increasing the smaller the discount factor becomes. We hypothesize that this result is driven by the existence of complex patterns of returns that are constantly changing and thus cannot be captured by relying on long-lasting experiences or static trading strategies.

UR - http://dx.doi.org/10.1109/CEC.2011.5949617

U2 - 10.1109/CEC.2011.5949617

DO - 10.1109/CEC.2011.5949617

M3 - Chapter

SN - 978-1-4244-7834-7

T3 - 2011 IEEE Congress of Evolutionary Computation, CEC 2011

SP - 186

EP - 191

BT - 2011 IEEE Congress of Evolutionary Computation, CEC 2011

PB - IEEE

CY - Piscataway, NJ

ER -