Prediction of stock price movements based on concept map information

A. Soni; N.J.P. Eck, van; U. Kaymak

doi:10.1109/MCDM.2007.369438

Prediction of stock price movements based on concept map information

A. Soni, N.J.P. Eck, van, U. Kaymak

Information Systems IE&IS

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

11 Citations (Scopus)

1 Downloads (Pure)

Abstract

Visualization of textual data may reveal interesting properties regarding the information conveyed in a group of documents. In this paper, we study whether the structure revealed by a visualization method can be used as inputs for improved classifiers. In particular, we study whether the locations of news items on a concept map could be used as inputs for improving the prediction of stock price movements from the news. We propose a method based on information visualization and text classification for achieving this. We apply the proposed approach to the prediction of the stock price movements of companies within the oil and natural gas sector. In a case study, we show that our proposed approach performs better than a naive approach and a bag-of-words approach

Original language	English
Title of host publication	IEEE Symposium on Computational Intelligence in Multicriteria Decision Making, 1-5 April 2007, Honolulu
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	205-211
ISBN (Print)	1-4244-0702-8
DOIs	https://doi.org/10.1109/MCDM.2007.369438
Publication status	Published - 2007

Access to Document

10.1109/MCDM.2007.369438

Cite this

@inproceedings{96bd12c06ec34e84a44e8c75e79c4d2a,

title = "Prediction of stock price movements based on concept map information",

abstract = "Visualization of textual data may reveal interesting properties regarding the information conveyed in a group of documents. In this paper, we study whether the structure revealed by a visualization method can be used as inputs for improved classifiers. In particular, we study whether the locations of news items on a concept map could be used as inputs for improving the prediction of stock price movements from the news. We propose a method based on information visualization and text classification for achieving this. We apply the proposed approach to the prediction of the stock price movements of companies within the oil and natural gas sector. In a case study, we show that our proposed approach performs better than a naive approach and a bag-of-words approach",

author = "A. Soni and {Eck, van}, N.J.P. and U. Kaymak",

year = "2007",

doi = "10.1109/MCDM.2007.369438",

language = "English",

isbn = "1-4244-0702-8",

pages = "205--211",

booktitle = "IEEE Symposium on Computational Intelligence in Multicriteria Decision Making, 1-5 April 2007, Honolulu",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

}

Prediction of stock price movements based on concept map information. / Soni, A.; Eck, van, N.J.P.; Kaymak, U.
IEEE Symposium on Computational Intelligence in Multicriteria Decision Making, 1-5 April 2007, Honolulu. Piscataway: Institute of Electrical and Electronics Engineers, 2007. p. 205-211.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Prediction of stock price movements based on concept map information

AU - Soni, A.

AU - Eck, van, N.J.P.

AU - Kaymak, U.

PY - 2007

Y1 - 2007

N2 - Visualization of textual data may reveal interesting properties regarding the information conveyed in a group of documents. In this paper, we study whether the structure revealed by a visualization method can be used as inputs for improved classifiers. In particular, we study whether the locations of news items on a concept map could be used as inputs for improving the prediction of stock price movements from the news. We propose a method based on information visualization and text classification for achieving this. We apply the proposed approach to the prediction of the stock price movements of companies within the oil and natural gas sector. In a case study, we show that our proposed approach performs better than a naive approach and a bag-of-words approach

AB - Visualization of textual data may reveal interesting properties regarding the information conveyed in a group of documents. In this paper, we study whether the structure revealed by a visualization method can be used as inputs for improved classifiers. In particular, we study whether the locations of news items on a concept map could be used as inputs for improving the prediction of stock price movements from the news. We propose a method based on information visualization and text classification for achieving this. We apply the proposed approach to the prediction of the stock price movements of companies within the oil and natural gas sector. In a case study, we show that our proposed approach performs better than a naive approach and a bag-of-words approach

U2 - 10.1109/MCDM.2007.369438

DO - 10.1109/MCDM.2007.369438

M3 - Conference contribution

SN - 1-4244-0702-8

SP - 205

EP - 211

BT - IEEE Symposium on Computational Intelligence in Multicriteria Decision Making, 1-5 April 2007, Honolulu

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

ER -

Prediction of stock price movements based on concept map information

Abstract

Access to Document

Fingerprint

Cite this