Short-term stock price analysis based on order book information

Kenichi Yoshida, Akito Sakurai

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Efficient market hypothesis is widely accepted in financial market studies and entails the unpredictability of future stock prices. In this study, we show that a simple analysis can classify short-term stock price changes with an 82.9% accuracy. Our analysis uses the order book information of high-frequency trading. The volume of high-frequency trading, which is responsible for short-term stock price changes, is increasing dramatically; therefore, our study suggests the importance of analyzing short-term market fluctuations, an aspect that is not well studied in conventional market theories. The experimental results also suggest the importance of the new data representation and analysis methods we propose, neither of which have been thoroughly investigated in conventional financial studies.

Original languageEnglish
Pages (from-to)683-692
Number of pages10
JournalTransactions of the Japanese Society for Artificial Intelligence
Volume30
Issue number5
DOIs
Publication statusPublished - 2015 Aug 27

Fingerprint

Financial markets

Keywords

  • Efficient market hypothesis
  • High-frequency trading
  • Stock market prediction
  • Technical analysis
  • Time series analysis

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Cite this

Short-term stock price analysis based on order book information. / Yoshida, Kenichi; Sakurai, Akito.

In: Transactions of the Japanese Society for Artificial Intelligence, Vol. 30, No. 5, 27.08.2015, p. 683-692.

Research output: Contribution to journalArticle

@article{fbabac879fbd4c04b2f0d714e761ae4d,
title = "Short-term stock price analysis based on order book information",
abstract = "Efficient market hypothesis is widely accepted in financial market studies and entails the unpredictability of future stock prices. In this study, we show that a simple analysis can classify short-term stock price changes with an 82.9{\%} accuracy. Our analysis uses the order book information of high-frequency trading. The volume of high-frequency trading, which is responsible for short-term stock price changes, is increasing dramatically; therefore, our study suggests the importance of analyzing short-term market fluctuations, an aspect that is not well studied in conventional market theories. The experimental results also suggest the importance of the new data representation and analysis methods we propose, neither of which have been thoroughly investigated in conventional financial studies.",
keywords = "Efficient market hypothesis, High-frequency trading, Stock market prediction, Technical analysis, Time series analysis",
author = "Kenichi Yoshida and Akito Sakurai",
year = "2015",
month = "8",
day = "27",
doi = "10.1527/tjsai.30_683",
language = "English",
volume = "30",
pages = "683--692",
journal = "Transactions of the Japanese Society for Artificial Intelligence",
issn = "1346-0714",
publisher = "Japanese Society for Artificial Intelligence",
number = "5",

}

TY - JOUR

T1 - Short-term stock price analysis based on order book information

AU - Yoshida, Kenichi

AU - Sakurai, Akito

PY - 2015/8/27

Y1 - 2015/8/27

N2 - Efficient market hypothesis is widely accepted in financial market studies and entails the unpredictability of future stock prices. In this study, we show that a simple analysis can classify short-term stock price changes with an 82.9% accuracy. Our analysis uses the order book information of high-frequency trading. The volume of high-frequency trading, which is responsible for short-term stock price changes, is increasing dramatically; therefore, our study suggests the importance of analyzing short-term market fluctuations, an aspect that is not well studied in conventional market theories. The experimental results also suggest the importance of the new data representation and analysis methods we propose, neither of which have been thoroughly investigated in conventional financial studies.

AB - Efficient market hypothesis is widely accepted in financial market studies and entails the unpredictability of future stock prices. In this study, we show that a simple analysis can classify short-term stock price changes with an 82.9% accuracy. Our analysis uses the order book information of high-frequency trading. The volume of high-frequency trading, which is responsible for short-term stock price changes, is increasing dramatically; therefore, our study suggests the importance of analyzing short-term market fluctuations, an aspect that is not well studied in conventional market theories. The experimental results also suggest the importance of the new data representation and analysis methods we propose, neither of which have been thoroughly investigated in conventional financial studies.

KW - Efficient market hypothesis

KW - High-frequency trading

KW - Stock market prediction

KW - Technical analysis

KW - Time series analysis

UR - http://www.scopus.com/inward/record.url?scp=84941643388&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84941643388&partnerID=8YFLogxK

U2 - 10.1527/tjsai.30_683

DO - 10.1527/tjsai.30_683

M3 - Article

VL - 30

SP - 683

EP - 692

JO - Transactions of the Japanese Society for Artificial Intelligence

JF - Transactions of the Japanese Society for Artificial Intelligence

SN - 1346-0714

IS - 5

ER -