Comparison of Genetic Algorithms for Trading Strategies
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21240%2F14%3A00213316" target="_blank" >RIV/68407700:21240/14:00213316 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1007/978-3-319-04298-5" target="_blank" >http://dx.doi.org/10.1007/978-3-319-04298-5</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-319-04298-5" target="_blank" >10.1007/978-3-319-04298-5</a>
Alternative languages
Result language
angličtina
Original language name
Comparison of Genetic Algorithms for Trading Strategies
Original language description
In this contribution, we describe and compare two genetic systems which create tading strategies. The first systém is based on the idea that the connection weight matrix of a neural network represents the genotype of and individual and can be changed bygenetic algorithm. The second systém uses genetic programming to derive trading strategies. As input data in our experiments, we used technical indicators of NASDAQ stocks. As output, the algorithms generate trading strategies, i.e. buy, hold, and sell signals. Our hypothesis that strategies obrained by genetic programming bring better results than buy-and-hold stratégy has been proven as statistically significant. We discuss our results and compare them to our previous experiments with fuzzy technology, fractal approach, and with simple technical indicator strategy.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
JD - Use of computers, robotics and its application
OECD FORD branch
—
Result continuities
Project
—
Continuities
V - Vyzkumna aktivita podporovana z jinych verejnych zdroju
Others
Publication year
2014
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
SOFSEM 2014: Theory and Practice of Computer Science
ISBN
978-3-319-04297-8
ISSN
0302-9743
e-ISSN
—
Number of pages
12
Pages from-to
383-394
Publisher name
Springer International Publishing AG
Place of publication
Cham
Event location
Nový Smokovec
Event date
Jan 25, 2014
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000342283300034