Last checked at 
(Repeats for wider distribution)
By Nate Raymond
NEW YORK, Nov 1 (Reuters) - When plumber Gary Pusey pleadedguilty in May to insider trading, it was a victory not just forNew York prosecutors but for a little-known squad inside theU.S. Securities and Exchange Commission that uses data analysisto spot unusual trading patterns.
Formed in 2010, the Analysis and Detection Center of theSEC's Market Abuse Unit culls through billions of rows oftrading data going back 15 years to identify individuals whohave made repeated, well-timed trades ahead of corporate news.
The new strategy is starting to show results, enabling theSEC to launch nine insider trading cases, around 7 percent ofcases the agency brought since 2014 against people who trade onconfidential corporate information.
It signals a shift in how the agency initiates insidertrading probes, which more often are launched based on referralsfrom Wall Street's self-regulator Financial Industry RegulatoryAuthority, or an informant's tip.
"It's essentially the new frontier," said Andrew Ceresney,the SEC's enforcement director. "We have tremendous amounts ofdata available to use, and we've been developing tools to takeadvantage of that."
That data was key to spotting trades by Pusey ahead of atleast 10 deals from 2014 to 2015 involving Barclays Plc, where his friend Steven McClatchey worked.
The SEC has also used data mining in a high-profile probe oftraders who it says made more than $100 million usinginformation obtained by Ukrainian hackers.
Others charged include former employees of law firm WilsonSonsini Goodrich & Rosati and investment bank Goldman SachsGroup Inc.. In August, former Perella Weinberg Partnersbanker Sean Stewart was convicted in a case credited to the SECunit. He denies wrongdoing and is expected to appeal.
10 BILLION ROWS OF TRADING DATA
The cases have come at a time when other U.S. and Europeanregulators have increasingly looked to find ways to takeadvantage Big Data in order to strengthen their enforcementoperations and market surveillance.
The United Kingdom's Financial Conduct Authority has inrecent years taken steps to develop technology to analyze largeamounts of data to pursue market abuse cases.
For the SEC, the six-year data-push has had the benefit ofgiving it some extra autonomy in pursuing insider trading probesbeyond the inquiries and referrals that self-regulatoryorganizations like FINRA produce for the agency.
"Why wait to do a referral when you could do itproactively?" said Daniel Hawke, a former chief of the SEC'sMarket Abuse Unit now at the law firm Arnold & Porter.
The SEC does not have a direct feed of the markets' tradingdata. Instead, it mines 10 billion rows of "blue sheet" data oftrades executed by brokerages that the agency gathered invarious investigations.
Analysts use a home-grown program called Artemis to analyzepatterns and relationships among multiple traders.
Joseph Sansone, a co-chief of the Market Abuse Unit, saidthe SEC in particular mines data to identify individuals whorepeatedly buy stock ahead of mergers, enabling the agency tofocus on repeat offenders.
"The ability to see pattern of multiple trades over a matterof months or years gives us confidence to invest resources intoinvestigations," he said.
The SEC also uses software from privately-held PalantirTechnologies, which identifies links between individuals andentities by connecting pieces of information from multiple datasources. In 2015, the agency awarded a $90 million, five-yearcontract to Palantir.
PLUMBER'S SCHEME
In Pusey's case, the SEC said that the data unit "detectedan illicit pattern of trading" by the plumber, who successfullytraded ahead of mergers involving companies that includedEntropic Communications Inc and CVS Health Corp.
In all of the deals, the target or acquirer were representedby Barclays. The SEC referred the case to federal prosecutors inManhattan and the Federal Bureau of Investigation.
In December 2015, Pusey, 47, began actively cooperating withthem, providing "detailed information" about his source,according to court papers.
In May, the FBI arrested that source, McClatchey, a closefriend of Pusey's who worked as a director at Barclays.
McClatchey, 58, pleaded guilty in July to tipping Pusey inexchange for money. He agreed to not appeal any sentence of fiveyears in prison or less and to forfeit $76,000.
Both men are set to be sentenced later this year. Lawyersfor the defendants did not respond to requests for comment.
To be sure, even with data mining, traditional investigativetechniques like enlisting cooperators and issuing subpoenas fordocuments remain key to building out a case. The SEC has in thepast acknowledged that it faces a challenge to keep up withtechnological advances in the securities markets it regulates,where spending by a number financial firms can surpass theagency's own expenditures.
And despite its early success, the SEC's ability to launchcases by data mining is also limited because it collects tradinginformation on an ad-hoc basis.
That is expected to change.
In April, the SEC released a plan to establish a databasethat stores every trade order, execution and cancellation. Knownas a "consolidated audit trail," it is a central repository thatis expected to begin getting data from stock exchanges and FINRAby late 2017.
Thomas Sporkin, a former senior SEC official with the lawfirm BuckleySandler, said that new database could significantlyadvance the SEC's ability to track suspicious trading.
"Doing surveillance for insider trading today -- it's likewe're in the early days of the automobile," he said. "What theconsolidated audit trail will provide is the future. It's theflying car." (Additional reporting by Rachel Armstrong and Huw Jones;Editing by Noeleen Walder and Edward Tobin)
