Analyzing stock market tick data using piecewise nonlinear model

Kyong Joo Oh, Kyoung Jae Kim

Research output: Contribution to journalArticle

64 Citations (Scopus)

Abstract

Trading in stock market indices has gained unprecedented popularity in major financial markets around the world. However, the prediction of stock price index is a very difficult problem because of the complexity of the stock market data. This study proposes stock trading model based on chaotic analysis and piecewise nonlinear model. The core component of the model is composed of four phases: The first phase determines time-lag size in input variables using chaotic analysis. The second phase detects successive change-points in the stock market data and the third phase forecasts the change-point group with backpropagation neural networks (BPNs). The final phase forecasts the output with BPN. The experimental results are encouraging and show the usefulness of the proposed model with respect to profitability.

Original languageEnglish
Pages (from-to)249-255
Number of pages7
JournalExpert Systems with Applications
Volume22
Issue number3
DOIs
Publication statusPublished - 2002 Jan 1

Fingerprint

Backpropagation
Neural networks
Point groups
Profitability
Financial markets

All Science Journal Classification (ASJC) codes

  • Engineering(all)
  • Computer Science Applications
  • Artificial Intelligence

Cite this

@article{69d9cdfec4f147118261eeb7583b6f68,
title = "Analyzing stock market tick data using piecewise nonlinear model",
abstract = "Trading in stock market indices has gained unprecedented popularity in major financial markets around the world. However, the prediction of stock price index is a very difficult problem because of the complexity of the stock market data. This study proposes stock trading model based on chaotic analysis and piecewise nonlinear model. The core component of the model is composed of four phases: The first phase determines time-lag size in input variables using chaotic analysis. The second phase detects successive change-points in the stock market data and the third phase forecasts the change-point group with backpropagation neural networks (BPNs). The final phase forecasts the output with BPN. The experimental results are encouraging and show the usefulness of the proposed model with respect to profitability.",
author = "Oh, {Kyong Joo} and Kim, {Kyoung Jae}",
year = "2002",
month = "1",
day = "1",
doi = "10.1016/S0957-4174(01)00058-6",
language = "English",
volume = "22",
pages = "249--255",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "3",

}

Analyzing stock market tick data using piecewise nonlinear model. / Oh, Kyong Joo; Kim, Kyoung Jae.

In: Expert Systems with Applications, Vol. 22, No. 3, 01.01.2002, p. 249-255.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Analyzing stock market tick data using piecewise nonlinear model

AU - Oh, Kyong Joo

AU - Kim, Kyoung Jae

PY - 2002/1/1

Y1 - 2002/1/1

N2 - Trading in stock market indices has gained unprecedented popularity in major financial markets around the world. However, the prediction of stock price index is a very difficult problem because of the complexity of the stock market data. This study proposes stock trading model based on chaotic analysis and piecewise nonlinear model. The core component of the model is composed of four phases: The first phase determines time-lag size in input variables using chaotic analysis. The second phase detects successive change-points in the stock market data and the third phase forecasts the change-point group with backpropagation neural networks (BPNs). The final phase forecasts the output with BPN. The experimental results are encouraging and show the usefulness of the proposed model with respect to profitability.

AB - Trading in stock market indices has gained unprecedented popularity in major financial markets around the world. However, the prediction of stock price index is a very difficult problem because of the complexity of the stock market data. This study proposes stock trading model based on chaotic analysis and piecewise nonlinear model. The core component of the model is composed of four phases: The first phase determines time-lag size in input variables using chaotic analysis. The second phase detects successive change-points in the stock market data and the third phase forecasts the change-point group with backpropagation neural networks (BPNs). The final phase forecasts the output with BPN. The experimental results are encouraging and show the usefulness of the proposed model with respect to profitability.

UR - http://www.scopus.com/inward/record.url?scp=0036533307&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036533307&partnerID=8YFLogxK

U2 - 10.1016/S0957-4174(01)00058-6

DO - 10.1016/S0957-4174(01)00058-6

M3 - Article

VL - 22

SP - 249

EP - 255

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 3

ER -