A dynamic pattern recognition approach based on neural network for stock time-series

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

7 Citations (Scopus)

Abstract

Pattern theorem in financial time-series is one of the most important technical analysis methods in financial prediction. Recent researches have achieved big progresses in identifying and recognizing time-series patterns. And most of the recent works on time-series deal with this task by using static approaches and mainly focus on the recognition accuracy, but considering that recognition of patterns in financial time-series, especially for stock time-series, are always time-consuming rather than pattern recognition in other fields, a dynamic recognition approach is more preferable so that investment on stock pattern become executable. In this paper we propose a dynamic approach for extracting and recognizing the patterns in stock-series. In our approach a slide window with flexible length is defined for extracting feature vertexes in stock-series, and in addition, a dynamic perceptual important point (PIP) locating method is proposed based on the PIP locating method for avoiding the computation expense problem and an artificial neural network (ANN) approach is involved for pattern recognition and window length identification.

Original languageEnglish
Title of host publication2009 World Congress on Nature and Biologically Inspired Computing, NABIC 2009 - Proceedings
Pages1552-1555
Number of pages4
DOIs
Publication statusPublished - 2009
Event2009 World Congress on Nature and Biologically Inspired Computing, NABIC 2009 - Coimbatore
Duration: 2009 Dec 92009 Dec 11

Other

Other2009 World Congress on Nature and Biologically Inspired Computing, NABIC 2009
CityCoimbatore
Period09/12/909/12/11

Fingerprint

Pattern recognition
Time series
Neural networks

Keywords

  • Dynamic approach
  • Finacial time-series
  • Pattern recognition
  • Stock series

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Software

Cite this

Zhou, B., & Furuzuki, T. (2009). A dynamic pattern recognition approach based on neural network for stock time-series. In 2009 World Congress on Nature and Biologically Inspired Computing, NABIC 2009 - Proceedings (pp. 1552-1555). [5393674] https://doi.org/10.1109/NABIC.2009.5393674

A dynamic pattern recognition approach based on neural network for stock time-series. / Zhou, Bo; Furuzuki, Takayuki.

2009 World Congress on Nature and Biologically Inspired Computing, NABIC 2009 - Proceedings. 2009. p. 1552-1555 5393674.

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

Zhou, B & Furuzuki, T 2009, A dynamic pattern recognition approach based on neural network for stock time-series. in 2009 World Congress on Nature and Biologically Inspired Computing, NABIC 2009 - Proceedings., 5393674, pp. 1552-1555, 2009 World Congress on Nature and Biologically Inspired Computing, NABIC 2009, Coimbatore, 09/12/9. https://doi.org/10.1109/NABIC.2009.5393674
Zhou B, Furuzuki T. A dynamic pattern recognition approach based on neural network for stock time-series. In 2009 World Congress on Nature and Biologically Inspired Computing, NABIC 2009 - Proceedings. 2009. p. 1552-1555. 5393674 https://doi.org/10.1109/NABIC.2009.5393674
Zhou, Bo ; Furuzuki, Takayuki. / A dynamic pattern recognition approach based on neural network for stock time-series. 2009 World Congress on Nature and Biologically Inspired Computing, NABIC 2009 - Proceedings. 2009. pp. 1552-1555
@inproceedings{73b248198ac84bc4904c09ef19058848,
title = "A dynamic pattern recognition approach based on neural network for stock time-series",
abstract = "Pattern theorem in financial time-series is one of the most important technical analysis methods in financial prediction. Recent researches have achieved big progresses in identifying and recognizing time-series patterns. And most of the recent works on time-series deal with this task by using static approaches and mainly focus on the recognition accuracy, but considering that recognition of patterns in financial time-series, especially for stock time-series, are always time-consuming rather than pattern recognition in other fields, a dynamic recognition approach is more preferable so that investment on stock pattern become executable. In this paper we propose a dynamic approach for extracting and recognizing the patterns in stock-series. In our approach a slide window with flexible length is defined for extracting feature vertexes in stock-series, and in addition, a dynamic perceptual important point (PIP) locating method is proposed based on the PIP locating method for avoiding the computation expense problem and an artificial neural network (ANN) approach is involved for pattern recognition and window length identification.",
keywords = "Dynamic approach, Finacial time-series, Pattern recognition, Stock series",
author = "Bo Zhou and Takayuki Furuzuki",
year = "2009",
doi = "10.1109/NABIC.2009.5393674",
language = "English",
isbn = "9781424456123",
pages = "1552--1555",
booktitle = "2009 World Congress on Nature and Biologically Inspired Computing, NABIC 2009 - Proceedings",

}

TY - GEN

T1 - A dynamic pattern recognition approach based on neural network for stock time-series

AU - Zhou, Bo

AU - Furuzuki, Takayuki

PY - 2009

Y1 - 2009

N2 - Pattern theorem in financial time-series is one of the most important technical analysis methods in financial prediction. Recent researches have achieved big progresses in identifying and recognizing time-series patterns. And most of the recent works on time-series deal with this task by using static approaches and mainly focus on the recognition accuracy, but considering that recognition of patterns in financial time-series, especially for stock time-series, are always time-consuming rather than pattern recognition in other fields, a dynamic recognition approach is more preferable so that investment on stock pattern become executable. In this paper we propose a dynamic approach for extracting and recognizing the patterns in stock-series. In our approach a slide window with flexible length is defined for extracting feature vertexes in stock-series, and in addition, a dynamic perceptual important point (PIP) locating method is proposed based on the PIP locating method for avoiding the computation expense problem and an artificial neural network (ANN) approach is involved for pattern recognition and window length identification.

AB - Pattern theorem in financial time-series is one of the most important technical analysis methods in financial prediction. Recent researches have achieved big progresses in identifying and recognizing time-series patterns. And most of the recent works on time-series deal with this task by using static approaches and mainly focus on the recognition accuracy, but considering that recognition of patterns in financial time-series, especially for stock time-series, are always time-consuming rather than pattern recognition in other fields, a dynamic recognition approach is more preferable so that investment on stock pattern become executable. In this paper we propose a dynamic approach for extracting and recognizing the patterns in stock-series. In our approach a slide window with flexible length is defined for extracting feature vertexes in stock-series, and in addition, a dynamic perceptual important point (PIP) locating method is proposed based on the PIP locating method for avoiding the computation expense problem and an artificial neural network (ANN) approach is involved for pattern recognition and window length identification.

KW - Dynamic approach

KW - Finacial time-series

KW - Pattern recognition

KW - Stock series

UR - http://www.scopus.com/inward/record.url?scp=77949611322&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77949611322&partnerID=8YFLogxK

U2 - 10.1109/NABIC.2009.5393674

DO - 10.1109/NABIC.2009.5393674

M3 - Conference contribution

AN - SCOPUS:77949611322

SN - 9781424456123

SP - 1552

EP - 1555

BT - 2009 World Congress on Nature and Biologically Inspired Computing, NABIC 2009 - Proceedings

ER -