The SEC’s Analysis and Detection Centre uses various pattern analysis methods on Big Data to detect insider trading.
Earlier in May this year, when Gary Pusey, a plumber, pleaded guilty to insider trading, it wasn’t a victory for just the New York prosecutors, but also to a little known squad in the SEC that uses data analysis to spot unusual trading patterns.
The SEC Analysis and Detection Centre was formed in 2010 as part of its Market Abuse Unit. They typically go through billions of rows of trading data going back to, as much as, 15 years to identify individuals who have made repeated well-timed trades ahead of corporate news.
This new strategy of analysing data to catch insider trading is starting to pay off: the SEC has filed 7 cases against individuals who have traded based on confidential corporate information.
This strategy of detecting data patterns in trading data signals a shift in the agency’s insider trading probes which were earlier, more often than not, based on an informant’s tip.
“It’s essentially the new frontier. We have tremendous amounts of data available to use, and we’ve been developing tools to take advantage of that,” said Andrew Ceresney, the SEC’s enforcement director.
The analysis was key in spotting trades by Pusey who traded ahead of at least 10 deals in 2014-2015, involving Barclays Plc, where his friend, Steven McClatchey worked.
Similarly, the SEC has also used data mining techniques to nail a high-profile case of insider trading wherein Ukrainian hackers made $100 million from hacked information.
Capitalising on Big Data
European and U.S. regulators are increasingly looking forward to finding ways to exploit the advantages of Big Data, in order to strengthen market surveillance and enforcement operations.
In Britain, the country’s Financial Conduct Authority, has in recent years, taken steps to develop technology to analyse vast amounts of data to pursue cases of market abuse.
In the U.S, the SEC’s 6-year push in Big Data has resulted in it receiving some extra autonomy in pursuing insider trading investigations beyond the normal inquiries and referrals that self-regulatory bodies like FINRA produce for the agency.
“Why wait to do a referral when you could do it proactively?” said Daniel Hawke, a former chief of the SEC’s Market Abuse Unit who now works at Arnold & Porter, a law firm.
Since the SEC itself does not have a direct feed of the market’s trading data,it mines the “blue sheet” data, brokers generate which it taps into for various investigations.
Its analysts use a home-grown program called Artemis to analyze patterns and relationships among multiple traders. Particularly those individuals who have repeatedly bought stocks ahead of mergers.
“The ability to see pattern of multiple trades over a matter of months or years gives us confidence to invest resources into investigations,” said Hawke.
The agency also uses software from Palantir Technologies to identify links between individuals and entities by connecting multiple disconnected data stream from various data sources. In 2015, the SEC had awarded a $90 million 5 year contract to Palantir to develop this capability.