Enhancement of trading rules on stock markets using Genetic Network Programming with Sarsa Learning

Yan Chen, Shingo Mabu, Kotaro Hirasawa, Takayuki Furuzuki

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

2 Citations (Scopus)

Abstract

In this paper, the enhancement of trading rules on stock markets using Genetic Network Programming (GNP) with Sarsa Learning is described. There are three important points in this paper: First, we use GNP with Sarsa learning as the basic algorithm while importance Indices and Candlestick Charts are introduced for efficient stock trading decision-making. Importance indices have been proposed to tell GNP the timing of buying and selling stocks. Second, to improve the performance of the proposed GNP-Sarsa algorithm, we develop a new method that can learn appropriate function describing the relation between the value of each technical index and the output of the importance index (IMX). This is an important point that devotes to the enhancement of the proposed GNP-Sarsa algorithm.Third, in order to create more efficient judgment functions to judge the current stock price appropriately, we develop a new way of classifying the candlestick chart body type. To confirm the effectiveness of the proposed method, we also compare the simulation results using GNP-Sarsa with other methods like traditional GNP and Buy&Hold method.

Original languageEnglish
Title of host publicationProceedings of the SICE Annual Conference
Pages2700-2707
Number of pages8
DOIs
Publication statusPublished - 2007
EventSICE(Society of Instrument and Control Engineers)Annual Conference, SICE 2007 - Takamatsu
Duration: 2007 Sep 172007 Sep 20

Other

OtherSICE(Society of Instrument and Control Engineers)Annual Conference, SICE 2007
CityTakamatsu
Period07/9/1707/9/20

Fingerprint

Describing functions
Sales
Decision making
Financial markets

Keywords

  • Candlestick chart
  • Genetic network programming
  • Reinforcement learning, sarsa
  • Stock trading model
  • Technical index

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Chen, Y., Mabu, S., Hirasawa, K., & Furuzuki, T. (2007). Enhancement of trading rules on stock markets using Genetic Network Programming with Sarsa Learning. In Proceedings of the SICE Annual Conference (pp. 2700-2707). [4421448] https://doi.org/10.1109/SICE.2007.4421448

Enhancement of trading rules on stock markets using Genetic Network Programming with Sarsa Learning. / Chen, Yan; Mabu, Shingo; Hirasawa, Kotaro; Furuzuki, Takayuki.

Proceedings of the SICE Annual Conference. 2007. p. 2700-2707 4421448.

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

Chen, Y, Mabu, S, Hirasawa, K & Furuzuki, T 2007, Enhancement of trading rules on stock markets using Genetic Network Programming with Sarsa Learning. in Proceedings of the SICE Annual Conference., 4421448, pp. 2700-2707, SICE(Society of Instrument and Control Engineers)Annual Conference, SICE 2007, Takamatsu, 07/9/17. https://doi.org/10.1109/SICE.2007.4421448
Chen Y, Mabu S, Hirasawa K, Furuzuki T. Enhancement of trading rules on stock markets using Genetic Network Programming with Sarsa Learning. In Proceedings of the SICE Annual Conference. 2007. p. 2700-2707. 4421448 https://doi.org/10.1109/SICE.2007.4421448
Chen, Yan ; Mabu, Shingo ; Hirasawa, Kotaro ; Furuzuki, Takayuki. / Enhancement of trading rules on stock markets using Genetic Network Programming with Sarsa Learning. Proceedings of the SICE Annual Conference. 2007. pp. 2700-2707
@inproceedings{5311a2deec6945dc90eb19cb625859c7,
title = "Enhancement of trading rules on stock markets using Genetic Network Programming with Sarsa Learning",
abstract = "In this paper, the enhancement of trading rules on stock markets using Genetic Network Programming (GNP) with Sarsa Learning is described. There are three important points in this paper: First, we use GNP with Sarsa learning as the basic algorithm while importance Indices and Candlestick Charts are introduced for efficient stock trading decision-making. Importance indices have been proposed to tell GNP the timing of buying and selling stocks. Second, to improve the performance of the proposed GNP-Sarsa algorithm, we develop a new method that can learn appropriate function describing the relation between the value of each technical index and the output of the importance index (IMX). This is an important point that devotes to the enhancement of the proposed GNP-Sarsa algorithm.Third, in order to create more efficient judgment functions to judge the current stock price appropriately, we develop a new way of classifying the candlestick chart body type. To confirm the effectiveness of the proposed method, we also compare the simulation results using GNP-Sarsa with other methods like traditional GNP and Buy&Hold method.",
keywords = "Candlestick chart, Genetic network programming, Reinforcement learning, sarsa, Stock trading model, Technical index",
author = "Yan Chen and Shingo Mabu and Kotaro Hirasawa and Takayuki Furuzuki",
year = "2007",
doi = "10.1109/SICE.2007.4421448",
language = "English",
isbn = "4907764286",
pages = "2700--2707",
booktitle = "Proceedings of the SICE Annual Conference",

}

TY - GEN

T1 - Enhancement of trading rules on stock markets using Genetic Network Programming with Sarsa Learning

AU - Chen, Yan

AU - Mabu, Shingo

AU - Hirasawa, Kotaro

AU - Furuzuki, Takayuki

PY - 2007

Y1 - 2007

N2 - In this paper, the enhancement of trading rules on stock markets using Genetic Network Programming (GNP) with Sarsa Learning is described. There are three important points in this paper: First, we use GNP with Sarsa learning as the basic algorithm while importance Indices and Candlestick Charts are introduced for efficient stock trading decision-making. Importance indices have been proposed to tell GNP the timing of buying and selling stocks. Second, to improve the performance of the proposed GNP-Sarsa algorithm, we develop a new method that can learn appropriate function describing the relation between the value of each technical index and the output of the importance index (IMX). This is an important point that devotes to the enhancement of the proposed GNP-Sarsa algorithm.Third, in order to create more efficient judgment functions to judge the current stock price appropriately, we develop a new way of classifying the candlestick chart body type. To confirm the effectiveness of the proposed method, we also compare the simulation results using GNP-Sarsa with other methods like traditional GNP and Buy&Hold method.

AB - In this paper, the enhancement of trading rules on stock markets using Genetic Network Programming (GNP) with Sarsa Learning is described. There are three important points in this paper: First, we use GNP with Sarsa learning as the basic algorithm while importance Indices and Candlestick Charts are introduced for efficient stock trading decision-making. Importance indices have been proposed to tell GNP the timing of buying and selling stocks. Second, to improve the performance of the proposed GNP-Sarsa algorithm, we develop a new method that can learn appropriate function describing the relation between the value of each technical index and the output of the importance index (IMX). This is an important point that devotes to the enhancement of the proposed GNP-Sarsa algorithm.Third, in order to create more efficient judgment functions to judge the current stock price appropriately, we develop a new way of classifying the candlestick chart body type. To confirm the effectiveness of the proposed method, we also compare the simulation results using GNP-Sarsa with other methods like traditional GNP and Buy&Hold method.

KW - Candlestick chart

KW - Genetic network programming

KW - Reinforcement learning, sarsa

KW - Stock trading model

KW - Technical index

UR - http://www.scopus.com/inward/record.url?scp=50249179750&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=50249179750&partnerID=8YFLogxK

U2 - 10.1109/SICE.2007.4421448

DO - 10.1109/SICE.2007.4421448

M3 - Conference contribution

SN - 4907764286

SN - 9784907764289

SP - 2700

EP - 2707

BT - Proceedings of the SICE Annual Conference

ER -