Evaluating the performance of adapting trading strategies with different memory lengths

Research output: Contribution to conferencePaper

4 Citations (Scopus)

Abstract

We propose a prediction model based on the minority game in which traders continuously evaluate a complete set of trading strategies with different memory lengths using the strategies’ past performance. Based on the chosen trading strategy they determine their prediction of the movement for the following time period of a single asset. We find empirically using stocks from the S&P500 that our prediction model yields a high success rate of over 51.5% and produces higher returns than a buy-and-hold strategy. Even when taking into account trading costs we find that using the predictions will generate superior investment portfolios.
Original languageEnglish
Pages711-718
Number of pages8
DOIs
Publication statusPublished - 2009
EventIntelligent Data Engineering and Automated Learning - IDEAL 2009 - Burgos, Spain
Duration: 23 Sep 200926 Sep 2009

Conference

ConferenceIntelligent Data Engineering and Automated Learning - IDEAL 2009
CountrySpain
CityBurgos
Period23/09/0926/09/09

Fingerprint

Prediction model
Prediction
Trading strategies
Minorities
Assets
Trading costs
Investment portfolio
Traders

Cite this

Krause, A. (2009). Evaluating the performance of adapting trading strategies with different memory lengths. 711-718. Paper presented at Intelligent Data Engineering and Automated Learning - IDEAL 2009, Burgos, Spain. https://doi.org/10.1007/978-3-642-04394-9_87

Evaluating the performance of adapting trading strategies with different memory lengths. / Krause, Andreas.

2009. 711-718 Paper presented at Intelligent Data Engineering and Automated Learning - IDEAL 2009, Burgos, Spain.

Research output: Contribution to conferencePaper

Krause, A 2009, 'Evaluating the performance of adapting trading strategies with different memory lengths' Paper presented at Intelligent Data Engineering and Automated Learning - IDEAL 2009, Burgos, Spain, 23/09/09 - 26/09/09, pp. 711-718. https://doi.org/10.1007/978-3-642-04394-9_87
Krause A. Evaluating the performance of adapting trading strategies with different memory lengths. 2009. Paper presented at Intelligent Data Engineering and Automated Learning - IDEAL 2009, Burgos, Spain. https://doi.org/10.1007/978-3-642-04394-9_87
Krause, Andreas. / Evaluating the performance of adapting trading strategies with different memory lengths. Paper presented at Intelligent Data Engineering and Automated Learning - IDEAL 2009, Burgos, Spain.8 p.
@conference{8124c5eb61c84cdcb888b394c9e07cc4,
title = "Evaluating the performance of adapting trading strategies with different memory lengths",
abstract = "We propose a prediction model based on the minority game in which traders continuously evaluate a complete set of trading strategies with different memory lengths using the strategies’ past performance. Based on the chosen trading strategy they determine their prediction of the movement for the following time period of a single asset. We find empirically using stocks from the S&P500 that our prediction model yields a high success rate of over 51.5{\%} and produces higher returns than a buy-and-hold strategy. Even when taking into account trading costs we find that using the predictions will generate superior investment portfolios.",
author = "Andreas Krause",
year = "2009",
doi = "10.1007/978-3-642-04394-9_87",
language = "English",
pages = "711--718",
note = "Intelligent Data Engineering and Automated Learning - IDEAL 2009 ; Conference date: 23-09-2009 Through 26-09-2009",

}

TY - CONF

T1 - Evaluating the performance of adapting trading strategies with different memory lengths

AU - Krause, Andreas

PY - 2009

Y1 - 2009

N2 - We propose a prediction model based on the minority game in which traders continuously evaluate a complete set of trading strategies with different memory lengths using the strategies’ past performance. Based on the chosen trading strategy they determine their prediction of the movement for the following time period of a single asset. We find empirically using stocks from the S&P500 that our prediction model yields a high success rate of over 51.5% and produces higher returns than a buy-and-hold strategy. Even when taking into account trading costs we find that using the predictions will generate superior investment portfolios.

AB - We propose a prediction model based on the minority game in which traders continuously evaluate a complete set of trading strategies with different memory lengths using the strategies’ past performance. Based on the chosen trading strategy they determine their prediction of the movement for the following time period of a single asset. We find empirically using stocks from the S&P500 that our prediction model yields a high success rate of over 51.5% and produces higher returns than a buy-and-hold strategy. Even when taking into account trading costs we find that using the predictions will generate superior investment portfolios.

UR - http://dx.doi.org/10.1007/978-3-642-04394-9_87

U2 - 10.1007/978-3-642-04394-9_87

DO - 10.1007/978-3-642-04394-9_87

M3 - Paper

SP - 711

EP - 718

ER -