Insider trading is a constant source of risk to investment banks. To mitigate this risk, banks must aggressively seek to detect and curtail insider trading, whether it occurs via internal employees, institutional customers, retail customers, or via proprietary managed funds.
Finding incidences of insider trading is a significant information challenge. The trading histories necessary to assemble patterns of behavior are scattered across different systems which are in turn governed by different organizations. Furthermore, trading data must be correlated with actionable information which may be in the form of published or proprietary news content, analyst research reports, or email, instant messaging, and phone conversations.
In this presentation, you will learn:
* What a semantic model for insider trading looks like * How a semantic model for insider trading facilitates rationalizing trade data from across systems and organizations * What a semantic solution for detecting insider trading looks like * How semantics makes it possible to bring in key sources of information on the fly