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. > >
Knowledge management is essential to modern organizations. Due to the information overload problem, managers are facing critical challenges in utilizing the data in organizations. Although several automated tools have been applied, previous applications often deem knowledge items independent and use solely contents, which may limit their analysis abilities. This study focuses on the process of knowledge evolution and proposes to incorporate this perspective into knowledge management tasks. Using a patent classification task as an example, we represent knowledge evolution processes with patent citations and introduce a labeled citation graph kernel to classify patents under a kernel-based machine learning framework. In the experimental study, our proposed approach shows more than 30 percent improvement in classification accuracy compared to traditional content-based methods. The approach can potentially affect the existing patent management procedures. Moreover, this research lends strong support to considering knowledge evolution processes in other knowledge management tasks.