Stock price change rate prediction by utilizing social network activities

Shangkun Deng, Takashi Mitsubuchi, Akito Sakurai

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Predicting stock price change rates for providing valuable information to investors is a challenging task. Individual participants may express their opinions in social network service (SNS) before or after their transactions in the market; we hypothesize that stock price change rate is better predicted by a function of social network service activities and technical indicators than by a function of just stock market activities. The hypothesis is tested by accuracy of predictions as well as performance of simulated trading because success or failure of prediction is better measured by profits or losses the investors gain or suffer. In this paper, we propose a hybrid model that combines multiple kernel learning (MKL) and genetic algorithm (GA). MKL is adopted to optimize the stock price change rate prediction models that are expressed in a multiple kernel linear function of different types of features extracted from different sources. GA is used to optimize the trading rules used in the simulated trading by fusing the return predictions and values of three well-known overbought and oversold technical indicators. Accumulated return and Sharpe ratio were used to test the goodness of performance of the simulated trading. Experimental results show that our proposed model performed better than other models including ones using state of the art techniques.

Original languageEnglish
Article number861641
JournalThe Scientific World Journal
Volume2014
DOIs
Publication statusPublished - 2014

Fingerprint

social network
Social Support
Social Work
prediction
Learning
genetic algorithm
Genetic algorithms
learning
stock market
Learning algorithms
Profitability
market
rate
price
indicator
services

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Environmental Science(all)
  • Medicine(all)

Cite this

Stock price change rate prediction by utilizing social network activities. / Deng, Shangkun; Mitsubuchi, Takashi; Sakurai, Akito.

In: The Scientific World Journal, Vol. 2014, 861641, 2014.

Research output: Contribution to journalArticle

Deng, Shangkun ; Mitsubuchi, Takashi ; Sakurai, Akito. / Stock price change rate prediction by utilizing social network activities. In: The Scientific World Journal. 2014 ; Vol. 2014.
@article{b43b7a38e3db4cb3bbdbd5f549518cfa,
title = "Stock price change rate prediction by utilizing social network activities",
abstract = "Predicting stock price change rates for providing valuable information to investors is a challenging task. Individual participants may express their opinions in social network service (SNS) before or after their transactions in the market; we hypothesize that stock price change rate is better predicted by a function of social network service activities and technical indicators than by a function of just stock market activities. The hypothesis is tested by accuracy of predictions as well as performance of simulated trading because success or failure of prediction is better measured by profits or losses the investors gain or suffer. In this paper, we propose a hybrid model that combines multiple kernel learning (MKL) and genetic algorithm (GA). MKL is adopted to optimize the stock price change rate prediction models that are expressed in a multiple kernel linear function of different types of features extracted from different sources. GA is used to optimize the trading rules used in the simulated trading by fusing the return predictions and values of three well-known overbought and oversold technical indicators. Accumulated return and Sharpe ratio were used to test the goodness of performance of the simulated trading. Experimental results show that our proposed model performed better than other models including ones using state of the art techniques.",
author = "Shangkun Deng and Takashi Mitsubuchi and Akito Sakurai",
year = "2014",
doi = "10.1155/2014/861641",
language = "English",
volume = "2014",
journal = "Scientific World Journal",
issn = "2356-6140",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - Stock price change rate prediction by utilizing social network activities

AU - Deng, Shangkun

AU - Mitsubuchi, Takashi

AU - Sakurai, Akito

PY - 2014

Y1 - 2014

N2 - Predicting stock price change rates for providing valuable information to investors is a challenging task. Individual participants may express their opinions in social network service (SNS) before or after their transactions in the market; we hypothesize that stock price change rate is better predicted by a function of social network service activities and technical indicators than by a function of just stock market activities. The hypothesis is tested by accuracy of predictions as well as performance of simulated trading because success or failure of prediction is better measured by profits or losses the investors gain or suffer. In this paper, we propose a hybrid model that combines multiple kernel learning (MKL) and genetic algorithm (GA). MKL is adopted to optimize the stock price change rate prediction models that are expressed in a multiple kernel linear function of different types of features extracted from different sources. GA is used to optimize the trading rules used in the simulated trading by fusing the return predictions and values of three well-known overbought and oversold technical indicators. Accumulated return and Sharpe ratio were used to test the goodness of performance of the simulated trading. Experimental results show that our proposed model performed better than other models including ones using state of the art techniques.

AB - Predicting stock price change rates for providing valuable information to investors is a challenging task. Individual participants may express their opinions in social network service (SNS) before or after their transactions in the market; we hypothesize that stock price change rate is better predicted by a function of social network service activities and technical indicators than by a function of just stock market activities. The hypothesis is tested by accuracy of predictions as well as performance of simulated trading because success or failure of prediction is better measured by profits or losses the investors gain or suffer. In this paper, we propose a hybrid model that combines multiple kernel learning (MKL) and genetic algorithm (GA). MKL is adopted to optimize the stock price change rate prediction models that are expressed in a multiple kernel linear function of different types of features extracted from different sources. GA is used to optimize the trading rules used in the simulated trading by fusing the return predictions and values of three well-known overbought and oversold technical indicators. Accumulated return and Sharpe ratio were used to test the goodness of performance of the simulated trading. Experimental results show that our proposed model performed better than other models including ones using state of the art techniques.

UR - http://www.scopus.com/inward/record.url?scp=84899426165&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84899426165&partnerID=8YFLogxK

U2 - 10.1155/2014/861641

DO - 10.1155/2014/861641

M3 - Article

VL - 2014

JO - Scientific World Journal

JF - Scientific World Journal

SN - 2356-6140

M1 - 861641

ER -