Main | Dr. Jennifer Bachner Discusses Best State Capitals on WalletHub »

GAB Forum: Machine Learning for Risk-Based Enforcement

This month's Government Analytics Breakfast Forum welcomed Jennifer Diamantis, Associate Director and Chief, Office of Market Intelligence and Austin Gerig, Assistant Director, Office of Research and Data Services from the Securities and Exchange Commission (SEC) to present their talk, Using Data Analysis and Machine Learning for Risk-Based Enforcement.

The presenters discussed how the SEC is using analytics to detect and gather evidence of insider trading and other market abuses.  Analytics allow the SEC to identify suspicious activity without receiving specific tips or complaints.  Further, the SEC is now better able to identify other individuals who may be involved with known suspicious activity. 

The SEC relies on a variety of statistical methods to make sense of the data they continuosly receive from the entities they regulate.  Using mostly open-source software such as R and Python, the SEC uses machine learning, text analytics, cluster analysis and network analysis to detect anomalies and abnormal behavior that may warrant further investigation.

The speakers were careful to note that these methods may, on occasion, produce false negative or false positives, so the results are carefully interpreted by those who have significant experience in the financial industry. 

The increased reliance on analytics has helped the SEC save resources by empowering them to accomplish more with less human capital.

A full recording of the presentation can be viewed here

PrintView Printer Friendly Version

EmailEmail Article to Friend

References (1)

References allow you to track sources for this article, as well as articles that were written in response to this article.

Reader Comments (1)

The information you provided is useful to everyone. I was really wondered about the information provided in the blog. Thanks for sharing valuable tips.

March 14, 2018 | Unregistered CommenterAPJ Smart Works

PostPost a New Comment

Enter your information below to add a new comment.

My response is on my own website »
Author Email (optional):
Author URL (optional):
Some HTML allowed: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <code> <em> <i> <strike> <strong>