Market impact analysis via sentimental transfer learning

Xiaodong LI; Haoran XIE; Tak Lam WONG; Fu Lee WANG

doi:10.1109/BIGCOMP.2017.7881754

Market impact analysis via sentimental transfer learning

Xiaodong LI, Haoran XIE, Tak Lam WONG, Fu Lee WANG

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

8 Citations (Scopus)

Abstract

The problem that how to improve the market impact prediction performances of predictors that are trained based on stocks with few market news is studied in this preliminary work. We propose sentimental transfer learning to transfer the knowledge learned from news-rich stocks that are within the same sector to the news-poor stocks. News articles of both kinds of stocks are mapped into the same feature space that are constructed by sentiment dimensions. New predictors are then trained in the sentimental space in contrast to the traditional ones. Experiments based on the data of Hong Kong stocks are conducted. From the early results, it could be seen that the proposed approach is convincing.

Original language	English
Title of host publication	2017 IEEE International Conference on Big Data and Smart Computing, BigComp 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	451-452
Number of pages	2
ISBN (Electronic)	9781509030156
DOIs	https://doi.org/10.1109/BIGCOMP.2017.7881754
Publication status	Published - 17 Mar 2017
Externally published	Yes
Event	2017 IEEE International Conference on Big Data and Smart Computing, BigComp 2017 - Jeju Island, Korea, Republic of Duration: 13 Feb 2017 → 16 Feb 2017

Conference

Conference	2017 IEEE International Conference on Big Data and Smart Computing, BigComp 2017
Country/Territory	Korea, Republic of
City	Jeju Island
Period	13/02/17 → 16/02/17

Access to Document

10.1109/BIGCOMP.2017.7881754

Cite this

@inproceedings{6616b8e2a23b4c84a3c828847b667e18,

title = "Market impact analysis via sentimental transfer learning",

abstract = "The problem that how to improve the market impact prediction performances of predictors that are trained based on stocks with few market news is studied in this preliminary work. We propose sentimental transfer learning to transfer the knowledge learned from news-rich stocks that are within the same sector to the news-poor stocks. News articles of both kinds of stocks are mapped into the same feature space that are constructed by sentiment dimensions. New predictors are then trained in the sentimental space in contrast to the traditional ones. Experiments based on the data of Hong Kong stocks are conducted. From the early results, it could be seen that the proposed approach is convincing.",

author = "Xiaodong LI and Haoran XIE and WONG, {Tak Lam} and WANG, {Fu Lee}",

year = "2017",

month = mar,

day = "17",

doi = "10.1109/BIGCOMP.2017.7881754",

language = "English",

pages = "451--452",

booktitle = "2017 IEEE International Conference on Big Data and Smart Computing, BigComp 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "2017 IEEE International Conference on Big Data and Smart Computing, BigComp 2017 ; Conference date: 13-02-2017 Through 16-02-2017",

}

LI, X, XIE, H, WONG, TL & WANG, FL 2017, Market impact analysis via sentimental transfer learning. in 2017 IEEE International Conference on Big Data and Smart Computing, BigComp 2017., 7881754, Institute of Electrical and Electronics Engineers Inc., pp. 451-452, 2017 IEEE International Conference on Big Data and Smart Computing, BigComp 2017, Jeju Island, Korea, Republic of, 13/02/17. https://doi.org/10.1109/BIGCOMP.2017.7881754

Market impact analysis via sentimental transfer learning. / LI, Xiaodong; XIE, Haoran; WONG, Tak Lam et al.
2017 IEEE International Conference on Big Data and Smart Computing, BigComp 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 451-452 7881754.

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

TY - GEN

T1 - Market impact analysis via sentimental transfer learning

AU - LI, Xiaodong

AU - XIE, Haoran

AU - WONG, Tak Lam

AU - WANG, Fu Lee

PY - 2017/3/17

Y1 - 2017/3/17

N2 - The problem that how to improve the market impact prediction performances of predictors that are trained based on stocks with few market news is studied in this preliminary work. We propose sentimental transfer learning to transfer the knowledge learned from news-rich stocks that are within the same sector to the news-poor stocks. News articles of both kinds of stocks are mapped into the same feature space that are constructed by sentiment dimensions. New predictors are then trained in the sentimental space in contrast to the traditional ones. Experiments based on the data of Hong Kong stocks are conducted. From the early results, it could be seen that the proposed approach is convincing.

AB - The problem that how to improve the market impact prediction performances of predictors that are trained based on stocks with few market news is studied in this preliminary work. We propose sentimental transfer learning to transfer the knowledge learned from news-rich stocks that are within the same sector to the news-poor stocks. News articles of both kinds of stocks are mapped into the same feature space that are constructed by sentiment dimensions. New predictors are then trained in the sentimental space in contrast to the traditional ones. Experiments based on the data of Hong Kong stocks are conducted. From the early results, it could be seen that the proposed approach is convincing.

UR - http://www.scopus.com/inward/record.url?scp=85017638408&partnerID=8YFLogxK

U2 - 10.1109/BIGCOMP.2017.7881754

DO - 10.1109/BIGCOMP.2017.7881754

M3 - Conference paper (refereed)

AN - SCOPUS:85017638408

SP - 451

EP - 452

BT - 2017 IEEE International Conference on Big Data and Smart Computing, BigComp 2017

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2017 IEEE International Conference on Big Data and Smart Computing, BigComp 2017

Y2 - 13 February 2017 through 16 February 2017

ER -

Market impact analysis via sentimental transfer learning

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this