A Commonsense Knowledge-Enabled Textual Analysis Approach for Financial Market Surveillance

doi:10.1287/ijoc.2015.0677

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 互联网大数据与信息安全

	A Commonsense Knowledge-Enabled Textual Analysis Approach for Financial Market Surveillance
	Li, Xin 1; Chen, Kun 2; Sun, Sherry X.; Fung, Terrance 3; Wang, Huaiqing 2; Zeng, Daniel D.4,5
发表期刊	INFORMS JOURNAL ON COMPUTING
	2016-03-01
卷号	28 期号:2 页码:278-294
文章类型	Article
摘要	Market surveillance systems (MSSs) are increasingly used to monitor trading activities in financial markets to maintain market integrity. Existing MSSs primarily focus on statistical analysis of market activity data and largely ignore textual market information, including, but not limited to, news reports and various social media. As suggested by both theoretical explorations in finance and prevailing market surveillance practice, unstructured market information holds major yet underexplored opportunities for surveillance. In this paper, we propose a news analysis approach with the help of commonsense knowledge to assess the risk of suspicious transactions identified in market activity analysis. Our approach explicitly models semantic relations between transactions and news articles and provides semantic references to words in news articles. We conducted experiments using data collected from a real-world market and found that our proposed approach significantly outperforms the existing methods, which are based on transaction characteristics or traditional textual analysis methods. Experiments also show that the performance advantage of the proposed approach mainly comes from the modeling of news-transaction relationships. The research contributes to the market surveillance literature and has significant practical implications.
关键词	Market Surveillance Text Mining Commonsense Knowledge Business Intelligence Intelligent Financial Systems
WOS标题词	Science & Technology ; Technology
DOI	10.1287/ijoc.2015.0677
关键词[WOS]	QUERY EXPANSION ; INVESTOR SENTIMENT ; MODEL ; INFORMATION ; LANGUAGE ; WORDNET ; SYSTEM ; TALK ; WEB
收录类别	SCI ; SSCI
语种	英语
项目资助者	City University of Hong Kong(SRG 7002898 ; NNSFC(71025001 ; GuangDong NSF(2015A030313876) ; Shenzhen Foundation Research(JCYJ20140417105742712) ; SRG 7004142) ; 71572169)
WOS研究方向	Computer Science ; Operations Research & Management Science
WOS类目	Computer Science, Interdisciplinary Applications ; Operations Research & Management Science
WOS记录号	WOS:000377110200007
引用统计	被引频次：6[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/12181
专题	多模态人工智能系统全国重点实验室_互联网大数据与信息安全
作者单位	1.City Univ Hong Kong, Coll Business, Dept Informat Syst, Hong Kong, Hong Kong, Peoples R China 2.South Univ Sci & Technol China, Dept Finance, Shenzhen 518000, Guangdong, Peoples R China 3.Secur & Futures Commiss Hong Kong, Hong Kong, Hong Kong, Peoples R China 4.Chinese Acad Sci, Inst Automat, Beijing 100864, Peoples R China 5.Univ Arizona, Dept Management Informat Syst, Tucson, AZ 85721 USA
推荐引用方式 GB/T 7714	Li, Xin,Chen, Kun,Sun, Sherry X.,et al. A Commonsense Knowledge-Enabled Textual Analysis Approach for Financial Market Surveillance[J]. INFORMS JOURNAL ON COMPUTING,2016,28(2):278-294.
APA	Li, Xin,Chen, Kun,Sun, Sherry X.,Fung, Terrance,Wang, Huaiqing,&Zeng, Daniel D..(2016).A Commonsense Knowledge-Enabled Textual Analysis Approach for Financial Market Surveillance.INFORMS JOURNAL ON COMPUTING,28(2),278-294.
MLA	Li, Xin,et al."A Commonsense Knowledge-Enabled Textual Analysis Approach for Financial Market Surveillance".INFORMS JOURNAL ON COMPUTING 28.2(2016):278-294.