Tensor-based learning for predicting stock movements

Qing Li, LiLing Jiang, Ping Li, Hsinchun Chen

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

15 Citations (Scopus)

Abstract

Stock movements are essentially driven by new information. Market data, financial news, and social sentiment are believed to have impacts on stock markets. To study the correlation between information and stock movements, previous works typically concatenate the features of different information sources into one super feature vector. However, such concatenated vector approaches treat each information source separately and ignore their interactions. In this article, we model the multi-faceted investors' information and their intrinsic links with tensors. To identify the nonlinear patterns between stock movements and new information, we propose a supervised tensor regression learning approach to investigate the joint impact of different information sources on stock markets. Experiments on CSI 100 stocks in the year 2011 show that our approach outperforms the state-of-the-art trading strategies.

Original languageEnglish (US)
Title of host publicationProceedings of the National Conference on Artificial Intelligence
PublisherAI Access Foundation
Pages1784-1790
Number of pages7
Volume3
ISBN (Print)9781577357018
StatePublished - Jun 1 2015
Event29th AAAI Conference on Artificial Intelligence, AAAI 2015 and the 27th Innovative Applications of Artificial Intelligence Conference, IAAI 2015 - Austin, United States
Duration: Jan 25 2015Jan 30 2015

Other

Other29th AAAI Conference on Artificial Intelligence, AAAI 2015 and the 27th Innovative Applications of Artificial Intelligence Conference, IAAI 2015
CountryUnited States
CityAustin
Period1/25/151/30/15

Fingerprint

Tensors
Experiments
Financial markets

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this

Li, Q., Jiang, L., Li, P., & Chen, H. (2015). Tensor-based learning for predicting stock movements. In Proceedings of the National Conference on Artificial Intelligence (Vol. 3, pp. 1784-1790). AI Access Foundation.

Tensor-based learning for predicting stock movements. / Li, Qing; Jiang, LiLing; Li, Ping; Chen, Hsinchun.

Proceedings of the National Conference on Artificial Intelligence. Vol. 3 AI Access Foundation, 2015. p. 1784-1790.

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

Li, Q, Jiang, L, Li, P & Chen, H 2015, Tensor-based learning for predicting stock movements. in Proceedings of the National Conference on Artificial Intelligence. vol. 3, AI Access Foundation, pp. 1784-1790, 29th AAAI Conference on Artificial Intelligence, AAAI 2015 and the 27th Innovative Applications of Artificial Intelligence Conference, IAAI 2015, Austin, United States, 1/25/15.
Li Q, Jiang L, Li P, Chen H. Tensor-based learning for predicting stock movements. In Proceedings of the National Conference on Artificial Intelligence. Vol. 3. AI Access Foundation. 2015. p. 1784-1790
Li, Qing ; Jiang, LiLing ; Li, Ping ; Chen, Hsinchun. / Tensor-based learning for predicting stock movements. Proceedings of the National Conference on Artificial Intelligence. Vol. 3 AI Access Foundation, 2015. pp. 1784-1790
@inproceedings{f4eff6af168947b0ad6928e61a295362,
title = "Tensor-based learning for predicting stock movements",
abstract = "Stock movements are essentially driven by new information. Market data, financial news, and social sentiment are believed to have impacts on stock markets. To study the correlation between information and stock movements, previous works typically concatenate the features of different information sources into one super feature vector. However, such concatenated vector approaches treat each information source separately and ignore their interactions. In this article, we model the multi-faceted investors' information and their intrinsic links with tensors. To identify the nonlinear patterns between stock movements and new information, we propose a supervised tensor regression learning approach to investigate the joint impact of different information sources on stock markets. Experiments on CSI 100 stocks in the year 2011 show that our approach outperforms the state-of-the-art trading strategies.",
author = "Qing Li and LiLing Jiang and Ping Li and Hsinchun Chen",
year = "2015",
month = "6",
day = "1",
language = "English (US)",
isbn = "9781577357018",
volume = "3",
pages = "1784--1790",
booktitle = "Proceedings of the National Conference on Artificial Intelligence",
publisher = "AI Access Foundation",

}

TY - GEN

T1 - Tensor-based learning for predicting stock movements

AU - Li, Qing

AU - Jiang, LiLing

AU - Li, Ping

AU - Chen, Hsinchun

PY - 2015/6/1

Y1 - 2015/6/1

N2 - Stock movements are essentially driven by new information. Market data, financial news, and social sentiment are believed to have impacts on stock markets. To study the correlation between information and stock movements, previous works typically concatenate the features of different information sources into one super feature vector. However, such concatenated vector approaches treat each information source separately and ignore their interactions. In this article, we model the multi-faceted investors' information and their intrinsic links with tensors. To identify the nonlinear patterns between stock movements and new information, we propose a supervised tensor regression learning approach to investigate the joint impact of different information sources on stock markets. Experiments on CSI 100 stocks in the year 2011 show that our approach outperforms the state-of-the-art trading strategies.

AB - Stock movements are essentially driven by new information. Market data, financial news, and social sentiment are believed to have impacts on stock markets. To study the correlation between information and stock movements, previous works typically concatenate the features of different information sources into one super feature vector. However, such concatenated vector approaches treat each information source separately and ignore their interactions. In this article, we model the multi-faceted investors' information and their intrinsic links with tensors. To identify the nonlinear patterns between stock movements and new information, we propose a supervised tensor regression learning approach to investigate the joint impact of different information sources on stock markets. Experiments on CSI 100 stocks in the year 2011 show that our approach outperforms the state-of-the-art trading strategies.

UR - http://www.scopus.com/inward/record.url?scp=84959885179&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959885179&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84959885179

SN - 9781577357018

VL - 3

SP - 1784

EP - 1790

BT - Proceedings of the National Conference on Artificial Intelligence

PB - AI Access Foundation

ER -