Genetic network programming with sarsa learning and its application to creating stock trading rules

Yan Chen, Shingo Mabu, Kotaro Hirasawa, Takayuki Furuzuki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

18 Citations (Scopus)

Abstract

In this paper, trading rules on stock market using the Genetic Network Programming (GNP) with Sarsa learning is described. GNP is an evolutionary computation, which represents its solutions using graph structures and has some useful features inherently. It has been clarified that GNP works well especially in dynamic environments since GNP can create quite compact programs and has an implicit memory function. In this paper, GNP is applied to creating a stock trading model. There are three important points: The first important point is to combine GNP with Sarsa Learning which is one of the reinforcement learning algorithms. Evolution-based methods evolve their programs after task execution because they must calculate fitness values, while reinforcement learning can change programs during task execution, therefore the programs can be created efficiently. The second important point is that GNP uses candlestick chart and selects appropriate technical indices to judge the timing of the buying and selling stocks. The third important point is that sub-nodes are used in each node to determine appropriate actions (buying/selling) and to select appropriate stock price information depending on the situation. In the simulations, the trading model is trained using the stock prices of 16 brands in 2001, 2002 and 2003. Then the generalization ability is tested using the stock prices in 2004. From the simulation results, it is clarified that the trading rules of the proposed method obtain much higher profits than Buy & Hold method and its effectiveness has been confirmed.

Original languageEnglish
Title of host publication2007 IEEE Congress on Evolutionary Computation, CEC 2007
Pages220-227
Number of pages8
DOIs
Publication statusPublished - 2007
Event2007 IEEE Congress on Evolutionary Computation, CEC 2007 -
Duration: 2007 Sep 252007 Sep 28

Other

Other2007 IEEE Congress on Evolutionary Computation, CEC 2007
Period07/9/2507/9/28

Fingerprint

Network Programming
Genetic Network
Reinforcement learning
Genetic Programming
Sales
Evolutionary algorithms
Stock Prices
Learning algorithms
Profitability
Data storage equipment
Reinforcement Learning
Implicit Function
Memory Function
Evolutionary Computation
Vertex of a graph
Stock Market
Dynamic Environment
Learning
Chart
Fitness

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Theoretical Computer Science

Cite this

Chen, Y., Mabu, S., Hirasawa, K., & Furuzuki, T. (2007). Genetic network programming with sarsa learning and its application to creating stock trading rules. In 2007 IEEE Congress on Evolutionary Computation, CEC 2007 (pp. 220-227). [4424475] https://doi.org/10.1109/CEC.2007.4424475

Genetic network programming with sarsa learning and its application to creating stock trading rules. / Chen, Yan; Mabu, Shingo; Hirasawa, Kotaro; Furuzuki, Takayuki.

2007 IEEE Congress on Evolutionary Computation, CEC 2007. 2007. p. 220-227 4424475.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chen, Y, Mabu, S, Hirasawa, K & Furuzuki, T 2007, Genetic network programming with sarsa learning and its application to creating stock trading rules. in 2007 IEEE Congress on Evolutionary Computation, CEC 2007., 4424475, pp. 220-227, 2007 IEEE Congress on Evolutionary Computation, CEC 2007, 07/9/25. https://doi.org/10.1109/CEC.2007.4424475
Chen Y, Mabu S, Hirasawa K, Furuzuki T. Genetic network programming with sarsa learning and its application to creating stock trading rules. In 2007 IEEE Congress on Evolutionary Computation, CEC 2007. 2007. p. 220-227. 4424475 https://doi.org/10.1109/CEC.2007.4424475
Chen, Yan ; Mabu, Shingo ; Hirasawa, Kotaro ; Furuzuki, Takayuki. / Genetic network programming with sarsa learning and its application to creating stock trading rules. 2007 IEEE Congress on Evolutionary Computation, CEC 2007. 2007. pp. 220-227
@inproceedings{0049dadd1bcc40cf904d51a8a518fde0,
title = "Genetic network programming with sarsa learning and its application to creating stock trading rules",
abstract = "In this paper, trading rules on stock market using the Genetic Network Programming (GNP) with Sarsa learning is described. GNP is an evolutionary computation, which represents its solutions using graph structures and has some useful features inherently. It has been clarified that GNP works well especially in dynamic environments since GNP can create quite compact programs and has an implicit memory function. In this paper, GNP is applied to creating a stock trading model. There are three important points: The first important point is to combine GNP with Sarsa Learning which is one of the reinforcement learning algorithms. Evolution-based methods evolve their programs after task execution because they must calculate fitness values, while reinforcement learning can change programs during task execution, therefore the programs can be created efficiently. The second important point is that GNP uses candlestick chart and selects appropriate technical indices to judge the timing of the buying and selling stocks. The third important point is that sub-nodes are used in each node to determine appropriate actions (buying/selling) and to select appropriate stock price information depending on the situation. In the simulations, the trading model is trained using the stock prices of 16 brands in 2001, 2002 and 2003. Then the generalization ability is tested using the stock prices in 2004. From the simulation results, it is clarified that the trading rules of the proposed method obtain much higher profits than Buy & Hold method and its effectiveness has been confirmed.",
author = "Yan Chen and Shingo Mabu and Kotaro Hirasawa and Takayuki Furuzuki",
year = "2007",
doi = "10.1109/CEC.2007.4424475",
language = "English",
isbn = "1424413400",
pages = "220--227",
booktitle = "2007 IEEE Congress on Evolutionary Computation, CEC 2007",

}

TY - GEN

T1 - Genetic network programming with sarsa learning and its application to creating stock trading rules

AU - Chen, Yan

AU - Mabu, Shingo

AU - Hirasawa, Kotaro

AU - Furuzuki, Takayuki

PY - 2007

Y1 - 2007

N2 - In this paper, trading rules on stock market using the Genetic Network Programming (GNP) with Sarsa learning is described. GNP is an evolutionary computation, which represents its solutions using graph structures and has some useful features inherently. It has been clarified that GNP works well especially in dynamic environments since GNP can create quite compact programs and has an implicit memory function. In this paper, GNP is applied to creating a stock trading model. There are three important points: The first important point is to combine GNP with Sarsa Learning which is one of the reinforcement learning algorithms. Evolution-based methods evolve their programs after task execution because they must calculate fitness values, while reinforcement learning can change programs during task execution, therefore the programs can be created efficiently. The second important point is that GNP uses candlestick chart and selects appropriate technical indices to judge the timing of the buying and selling stocks. The third important point is that sub-nodes are used in each node to determine appropriate actions (buying/selling) and to select appropriate stock price information depending on the situation. In the simulations, the trading model is trained using the stock prices of 16 brands in 2001, 2002 and 2003. Then the generalization ability is tested using the stock prices in 2004. From the simulation results, it is clarified that the trading rules of the proposed method obtain much higher profits than Buy & Hold method and its effectiveness has been confirmed.

AB - In this paper, trading rules on stock market using the Genetic Network Programming (GNP) with Sarsa learning is described. GNP is an evolutionary computation, which represents its solutions using graph structures and has some useful features inherently. It has been clarified that GNP works well especially in dynamic environments since GNP can create quite compact programs and has an implicit memory function. In this paper, GNP is applied to creating a stock trading model. There are three important points: The first important point is to combine GNP with Sarsa Learning which is one of the reinforcement learning algorithms. Evolution-based methods evolve their programs after task execution because they must calculate fitness values, while reinforcement learning can change programs during task execution, therefore the programs can be created efficiently. The second important point is that GNP uses candlestick chart and selects appropriate technical indices to judge the timing of the buying and selling stocks. The third important point is that sub-nodes are used in each node to determine appropriate actions (buying/selling) and to select appropriate stock price information depending on the situation. In the simulations, the trading model is trained using the stock prices of 16 brands in 2001, 2002 and 2003. Then the generalization ability is tested using the stock prices in 2004. From the simulation results, it is clarified that the trading rules of the proposed method obtain much higher profits than Buy & Hold method and its effectiveness has been confirmed.

UR - http://www.scopus.com/inward/record.url?scp=55749086694&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=55749086694&partnerID=8YFLogxK

U2 - 10.1109/CEC.2007.4424475

DO - 10.1109/CEC.2007.4424475

M3 - Conference contribution

AN - SCOPUS:55749086694

SN - 1424413400

SN - 9781424413409

SP - 220

EP - 227

BT - 2007 IEEE Congress on Evolutionary Computation, CEC 2007

ER -