Views on improving the integrity of global capital markets
23 October 2013

The Role of Data Analytics in SEC Fraud Investigations

In the face of rapid financial industry innovations, the SEC must continually update its technological resources to keep up with the speed and complexity in which transactions occur in the investment marketplace. To maintain pace with these industry developments, the regulator has drawn on its post-Madoff-era funding to invest in technology and hire industry specialists with strong quantitative analysis skills.

At the recent GIPS Standards Annual Conference, representatives from the SEC provided a fascinating look at how they use data analytics to identify potentially fraudulent activity, such as front running, insider trading, fraudulent investment performance reporting, and window dressing.

Sofia Hussain, senior forensic accountant in the SEC’s Boston Regional Office, Division of Enforcement, discussed how trading volume has exploded in recent years, creating the need for regulators to keep pace with and analyze vast quantities of data.

Hussain discussed two types of data analytics used in fraud investigations: link analysis and aberrational performance detection.

Link analysis, which looks for relationships between two disparate data sources, is particularly important in SEC investigations involving insider trading. Hussain presented a real world example whereby the SEC sought to identify through phone record analysis how two individuals obtained insider information and whether they had any connections to each other. Using link analysis software on thousands of lines of data, investigators were able to quickly identify all instances in which the two suspects had a phone call with someone in common. Back in the old days, SEC investigators would attempt to look at each record individually.

In a second example, Hussain — who focuses on using data analytics in investigations and previously was a forensic accountant at the U.S. Federal Bureau of Investigation — shared how link analysis was used to analyze large volumes of brokerage firm data to identify instances in which a particular corporation allegedly purchased and sold its own stock, with no significant gain or loss, to create a fictitiously high trading volume. This in turn allowed the company to fraudulently obtain bank financing.

Carolyn O’Brien, exam manager in the SEC’s Boston Regional Office, Office of Compliance Inspections and Examinations (OCIE) discussed how the SEC uses aberrational performance detection, which focuses on unexpected performance to both identify SEC examination candidates and to ensure compliance with certain regulations as part of an examination. Her previous experience includes investment performance analysis for a major teaching hospital’s endowment and pooled capital funds.

She presented an example in which a hedge fund’s reported results were significantly better than its peers throughout both good and bad markets. As part a joint investigation involving the OCIE, Division of Investment Management, Division of Economic and Risk Analysis, and Division of Enforcement, SEC investigators were able to determine that the hedge fund’s actual performance was significantly worse than its peers. Aberrational performance reviews such as these have been helpful in identifying intentional valuation misstatements, Ponzi schemes, and other alleged illicit activities before they otherwise would have been discovered.

The SEC also uses algorithms to analyze data contained within SEC filings to identify possible improprieties and can use various sources of public information — such as regulatory filings, media reports, websites, and third-party databases — to also identify which registrants to examine. It also runs quantitative analytic programs on trade data to see what lies beneath; for example, it can compare the output from quantitative models to the actual trading records to determine whether they’re in agreement.

It’s obvious from listening to the SEC speakers that the use and analysis of “big data” is a priority for the regulator. In fact, the SEC recently announced a new market structure website that will enable the public to analyze data from 13 U.S. equity exchanges through the Market Information Data Analytics System (MIDAS). The new website contains a data visualizations section that allows users to create their own charts as well as research papers based on the data obtained. The press release states the “website is just the beginning of this initiative with more studies and analyses to come.”

SEC Chair Mary Jo White also stressed the importance of technology in a recent speech: “The technology we are using is assisting us in many areas. We are using data analytics and related technology to enable us to conduct predictive analysis and spot trends, streamline our investigative efforts and leverage new data sources such as Form PF, which collects information from private funds — hedge funds, private equity funds — on, among other things, the type and size of assets they hold.

Stay tuned – we’ll continue to monitor developments in this space.

Related links:

GIPS Standards Conference: SEC Compliance Inspections and Examinations Update (Video)

SEC Announces Creation of New Office Within its Division of Economic and Risk Analysis (Press Release)

If you liked this post, consider subscribing to Market Integrity Insights.

Photo credit: ©

About the Author(s)
Ken Robinson, CFA, CIPM

Ken Robinson, CFA, CIPM, is a director of investment performance standards at CFA Institute. He helps maintain the GIPS standards by managing the interpretations process and developing guidance for new technical areas.

2 thoughts on “The Role of Data Analytics in SEC Fraud Investigations”

  1. Jenny says:

    Thanks for sharing!

  2. kavinn says:

    It has been pleasure information and I like to read your blog. And, glad to know about role of data analytics in SEC fraud.

Leave a Reply

Your email address will not be published.

By continuing to use the site, you agree to the use of cookies. more information

The cookie settings on this website are set to "allow cookies" to give you the best browsing experience possible. If you continue to use this website without changing your cookie settings or you click "Accept" below then you are consenting to this.