Stock Price Prediction by Deep Neural Generative Model of News Articles

Takashi MATSUBARA; Ryo AKITA; Kuniaki UEHARA

doi:10.1587/transinf.2016IIP0016

Stock Price Prediction by Deep Neural Generative Model of News Articles

Takashi MATSUBARA, Ryo AKITA, Kuniaki UEHARA

Full Text Views

0

Cite this

Summary :

In this study, we propose a deep neural generative model for predicting daily stock price movements given news articles. Approaches involving conventional technical analysis have been investigated to identify certain patterns in past price movements, which in turn helps to predict future price movements. However, the financial market is highly sensitive to specific events, including corporate buyouts, product releases, and the like. Therefore, recent research has focused on modeling relationships between these events that appear in the news articles and future price movements; however, a very large number of news articles are published daily, each article containing rich information, which results in overfitting to past price movements used for parameter adjustment. Given the above, we propose a model based on a generative model of news articles that includes price movement as a condition, thereby avoiding excessive overfitting thanks to the nature of the generative model. We evaluate our proposed model using historical price movements of Nikkei 225 and Standard & Poor's 500 Stock Index, confirming that our model predicts future price movements better than such conventional classifiers as support vector machines and multilayer perceptrons. Further, our proposed model extracts significant words from news articles that are directly related to future stock price movements.

Publication: IEICE TRANSACTIONS on Information Vol.E101-D No.4 pp.901-908

Publication Date: 2018/04/01

Publicized: 2018/01/19

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2016IIP0016

Type of Manuscript: Special Section PAPER (Special Section on Intelligent Information and Communication Technology and its Applications to Creative Activity Support)

Category: Datamining Technologies

Authors

Takashi MATSUBARA
  Kobe University
Ryo AKITA
  Kobe University
Kuniaki UEHARA
  Kobe University

Keyword

stock price prediction, news articles, deep learning, generative model

Cite this

Copy

Takashi MATSUBARA, Ryo AKITA, Kuniaki UEHARA, "Stock Price Prediction by Deep Neural Generative Model of News Articles" in IEICE TRANSACTIONS on Information, vol. E101-D, no. 4, pp. 901-908, April 2018, doi: 10.1587/transinf.2016IIP0016.
Abstract: In this study, we propose a deep neural generative model for predicting daily stock price movements given news articles. Approaches involving conventional technical analysis have been investigated to identify certain patterns in past price movements, which in turn helps to predict future price movements. However, the financial market is highly sensitive to specific events, including corporate buyouts, product releases, and the like. Therefore, recent research has focused on modeling relationships between these events that appear in the news articles and future price movements; however, a very large number of news articles are published daily, each article containing rich information, which results in overfitting to past price movements used for parameter adjustment. Given the above, we propose a model based on a generative model of news articles that includes price movement as a condition, thereby avoiding excessive overfitting thanks to the nature of the generative model. We evaluate our proposed model using historical price movements of Nikkei 225 and Standard & Poor's 500 Stock Index, confirming that our model predicts future price movements better than such conventional classifiers as support vector machines and multilayer perceptrons. Further, our proposed model extracts significant words from news articles that are directly related to future stock price movements.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2016IIP0016/_p

Copy

@ARTICLE{e101-d_4_901,
author={Takashi MATSUBARA, Ryo AKITA, Kuniaki UEHARA, },
journal={IEICE TRANSACTIONS on Information},
title={Stock Price Prediction by Deep Neural Generative Model of News Articles},
year={2018},
volume={E101-D},
number={4},
pages={901-908},
abstract={In this study, we propose a deep neural generative model for predicting daily stock price movements given news articles. Approaches involving conventional technical analysis have been investigated to identify certain patterns in past price movements, which in turn helps to predict future price movements. However, the financial market is highly sensitive to specific events, including corporate buyouts, product releases, and the like. Therefore, recent research has focused on modeling relationships between these events that appear in the news articles and future price movements; however, a very large number of news articles are published daily, each article containing rich information, which results in overfitting to past price movements used for parameter adjustment. Given the above, we propose a model based on a generative model of news articles that includes price movement as a condition, thereby avoiding excessive overfitting thanks to the nature of the generative model. We evaluate our proposed model using historical price movements of Nikkei 225 and Standard & Poor's 500 Stock Index, confirming that our model predicts future price movements better than such conventional classifiers as support vector machines and multilayer perceptrons. Further, our proposed model extracts significant words from news articles that are directly related to future stock price movements.},
keywords={},
doi={10.1587/transinf.2016IIP0016},
ISSN={1745-1361},
month={April},}

Copy

TY - JOUR
TI - Stock Price Prediction by Deep Neural Generative Model of News Articles
T2 - IEICE TRANSACTIONS on Information
SP - 901
EP - 908
AU - Takashi MATSUBARA
AU - Ryo AKITA
AU - Kuniaki UEHARA
PY - 2018
DO - 10.1587/transinf.2016IIP0016
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2018
AB - In this study, we propose a deep neural generative model for predicting daily stock price movements given news articles. Approaches involving conventional technical analysis have been investigated to identify certain patterns in past price movements, which in turn helps to predict future price movements. However, the financial market is highly sensitive to specific events, including corporate buyouts, product releases, and the like. Therefore, recent research has focused on modeling relationships between these events that appear in the news articles and future price movements; however, a very large number of news articles are published daily, each article containing rich information, which results in overfitting to past price movements used for parameter adjustment. Given the above, we propose a model based on a generative model of news articles that includes price movement as a condition, thereby avoiding excessive overfitting thanks to the nature of the generative model. We evaluate our proposed model using historical price movements of Nikkei 225 and Standard & Poor's 500 Stock Index, confirming that our model predicts future price movements better than such conventional classifiers as support vector machines and multilayer perceptrons. Further, our proposed model extracts significant words from news articles that are directly related to future stock price movements.
ER -