Ontologies play a key role in all aspects of information management within different domains as they provide a common and usable representation of the domain knowledge. The objective of the ontology is to describe the different classes (terms and vocabularies), and to define their relationships according to specific domain rules, in order to describe the knowledge of domain in a generic way. Ontology can be useful in many ways. One contemporary use is as a framework to represent information of domain in useful way. It enables computers to process its contents as it offers a way to give information about common representation and semantics to domains. In particular, it helps in bridging the communication gaps between humans and software systems through representing a shared and common understanding of a domain.Researchers in the field of artificial intelligence (AI), business intelligence (BI), and knowledge management have recognized that capturing knowledge is the key to building large and powerful systems. It is argued that ontologies could create new computational models which enable certain kinds of automation of information representation. While the sheer size and scale of data has been growing exponentially, these data presents its own challenge. Knowing how to first understand the data, garnering information and knowledge from it, and then intelligently combine it with other data sets means that there is a need to accurately represent this data and effectively allows identifying insightful information out of context.In the context of financial markets, there is a wealth of knowledge that is generated and it is important that this knowledge is managed and communicated efficiently and effectively. This is especially true in the context of monitoring and surveillance due to the changes in the structure, connectivity and operation of financial markets and the increased complexity in dealing with possible fraud cases. An ontology addressing the needs for market monitoring and surveillance could help support better the increased requirements of market operators, brokers and regulators to ensure that markets operate in an efficient way.The report discusses the development of ontology for financial markets monitoring and surveillance. The proposed ontology brings together existing domain knowledge from previous efforts together with new knowledge derived from the analysis of unstructured sources based on existing fraud cases reported by SEC. The ontology is represented using semantic representation techniques and contains a comprehensive set of concepts that could help analysts to understand financial fraud practices, assist open investigation by managing relevant facts gathered for case investigations, informing detection and pattern monitoring techniques, developing prevention practices, and sharing manipulation patterns from prosecuted cases with investigators and relevant stakeholders.The ontology is evaluated through specific case studies to show the applicability of the ontology to help users in the market monitoring surveillance systems. In particular, the three cases are considered as intelligent systems that extract information from unstructured sources based on the financial ontology. First case aims to provide an empirical evidence of how text mining could be integrated with the proposed ontology to improve the efficiency of extracting financial fraud concepts from Security Exchange Commission (SEC) litigation releases and demonstrating the published prosecuted cases from SEC website in appropriate knowledge base. Second case aims to demonstrate how text mining techniques could automatically extract key attributes and characteristics of different unstructured sources generated as part of ’touting campaigns’. Last case aims to describe business intelligence (BI) service system for a financial market monitoring and surveillance system in order to produce alarms for possible securities fraud cases. The evaluation of the proposed ontology with the BI service system is carried out through an exemplar case that relates to a real case from the over-the-counter (OTC) market and which was prosecuted by SEC.
[1]
Sehl Mellouli,et al.
An ontology for representing financial headline news
,
2010,
J. Web Semant..
[2]
John Kingston,et al.
Towards a Financial Fraud Ontology: A Legal Modelling Approach
,
2004,
Artificial Intelligence and Law.
[3]
Stephen Shaoyi Liao,et al.
An ontology based framework for mining dependence relationships between news and financial instruments
,
2011,
Expert Syst. Appl..
[4]
Dieter Fensel,et al.
Towards the Semantic Web
,
2002
.
[5]
Hilary Cheng,et al.
An ontology-based business intelligence application in a financial knowledge management system
,
2009,
Expert Syst. Appl..