Design Theory for Market Surveillance Systems

Abstract

Market surveillance systems (MSSs) are information systems that monitor financial markets to combat market abuses. Existing MSSs focus mainly on analyzing trading activities and are often developed through a trial-and-error approach by screening data mining algorithms and features. The void of theoretical direction limits the effectiveness of MSSs and calls for the development of a design theory based on a thorough examination of the meta-requirements of MSSs. Based on the efficient market hypothesis and text understanding theory, this paper argues that market information analysis should be incorporated into MSSs and commonsense knowledge should be employed to connect related events to transactions and provide reference concepts for understanding market context and assessing transaction risk. We show the effectiveness of this proposed design theory through developing and evaluating a prototype system in the context of a real-world stock exchange market. By taking a theory-driven approach, this research shows the possibility and provides guidelines on the use of market information analysis to alleviate the market surveillance problem, which has significant implications for financial markets and the economy given the explosive growth of illegal trading activities worldwide.

Key words and phrases:

• design theory
• market surveillance systems
• text mining
• financial markets
• efficient market hypothesis
• text understanding theory

Notes

1. Since news is the major influential market information, we use news and market information interchangeably.

2. We also experimented with POS features using the Stanford POS tagger [65], sentiment features using SentiWordNet [6], and features from different parts of news, such as news title or news content as in previous financial text mining studies [42]. These features do not provide significant performance difference. We thus use the basic representation in this paper.

3. We do not do binary classification since we do not know the threshold used in industry in market activity analysis.

Additional information

Notes on contributors

Xin Li

Xin Li is an assistant professor in the Department of Information Systems at the City University of Hong Kong. He received his Ph.D. in Management Information Systems from the University of Arizona, and his Bachelor’s and Master’s degrees from the Department of Automation at Tsinghua University, China. His research interests include business intelligence and knowledge discovery, social network analysis, social media, and e-commerce. His work has appeared in the Journal of Management Information Systems, Decision Support Systems, ACM Transactions on Management Information Systems, Journal of the American Society for Information Science and Technology, and various IEEE Transactions, among other venues.

Sherry X. Sun

Sherry X. Sun holds a Ph.D. degree in management and an M.S. degree in management information systems from the University of Arizona. Her research focuses on the construction of computational methodologies and tools for the management of enterprise information systems. She has published in journals such as Information Systems Research, IEEE Transactions on Systems, Man, and Cybernetics, Information Sciences, Information Systems Frontier, and others.

Kun Chen

Kun Chen (corresponding author; [email protected]) is an assistant professor in the Department of Financial Mathematics and Financial Engineering at South University of Science and Technology of China in Shenzhen. She received her Ph.D. from the Department of Information Systems at the City University of Hong Kong.

Terrance Fung

Terrance Fung works for the Securities and Futures Commission of Hong Kong. He received his Ph.D. from the Department of Information Systems at the City University of Hong Kong.

Huaiqing Wang

Huaiqing Wang is a professor in the Department of Financial Mathematics and Financial Engineering at South University of Science and Technology of China, in Shenzhen. He is also the honorary dean and a guest professor in the School of Information Engineering, Wuhan University of Technology, China. He received his Ph.D. from the University of Manchester, UK. He specializes in the research of financial intelligence and intelligent systems, such as intelligent financial systems, intelligent learning systems, business process management systems, knowledge management systems, and conceptual modeling and ontology. He has published more than 70 papers in well-known scholarly journals.