Stories
Slash Boxes
Comments

SoylentNews is people

posted by janrinok on Sunday November 10 2019, @12:18AM   Printer-friendly
from the doesn't-mean-that-it-will-catch-them dept.

Submitted via IRC for SoyCow1337

AI will now watch for fraudsters on the world's largest stock exchange

The Nasdaq stock market is an attractive target for fraudsters. As the world's largest stock exchange by volume, it must be constantly monitored for attempts to illicitly beat the system. These can include manipulations to inflate a stock's closing price; churning (rapidly buying and selling stocks) to give the false impression of a lot of activity; and spoofing (placing a large buy or sell order with no intention of actually executing) to create artificially high demand.

That monitoring is now being aided by artificial intelligence, Nasdaq, the stock market's parent company, announced today. A new deep-learning system is working in tandem with human analysts to keep watch over roughly 17.5 million trades per day.

The system augments an existing software surveillance system that uses statistics and rules to flag any signs of market abuse. In the US equity market, for example, the old system issued around 1,000 alerts per day for human analysts to investigate, says Martina Rejsjo, the head of market surveillance for Nasdaq's North America equities. Only a fraction of these cases would subsequently be confirmed as fraud and result in heavy fines.

The new system should have a number of advantages. First, Nasdaq claims it will be more accurate at identifying patterns of abuse, reducing the burden on human analysts. Second, it will be better at detecting more complex patterns of abuse, particularly spoofing, which Nasdaq believes will become increasingly common.


Original Submission

This discussion has been archived. No new comments can be posted.
Display Options Threshold/Breakthrough Mark All as Read Mark All as Unread
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
(1)
  • (Score: 1, Insightful) by Anonymous Coward on Sunday November 10 2019, @12:23AM (1 child)

    by Anonymous Coward on Sunday November 10 2019, @12:23AM (#918466)

    There are probably 1000 alerts per day just for Goldman Sachs.

    • (Score: 0) by Anonymous Coward on Sunday November 10 2019, @12:36AM

      by Anonymous Coward on Sunday November 10 2019, @12:36AM (#918475)

      file footage [youtube.com]

  • (Score: 2, Insightful) by Frosty Piss on Sunday November 10 2019, @12:31AM (4 children)

    by Frosty Piss (4971) on Sunday November 10 2019, @12:31AM (#918472)

    They have some complex algorithm that improves its accuracy with input from human analysts? This is what “AI” is?

    • (Score: 3, Insightful) by captain normal on Sunday November 10 2019, @12:34AM (3 children)

      by captain normal (2205) on Sunday November 10 2019, @12:34AM (#918474)

      Right...how can you prevent fraud in a system based on fraud?

      --
      Everyone is entitled to his own opinion, but not to his own facts"- --Daniel Patrick Moynihan--
      • (Score: 3, Interesting) by krishnoid on Sunday November 10 2019, @12:51AM (2 children)

        by krishnoid (1156) on Sunday November 10 2019, @12:51AM (#918477)

        Enforcing the laws of physics [theverge.com], to start with?

        • (Score: 2) by maxwell demon on Sunday November 10 2019, @04:57PM (1 child)

          by maxwell demon (1608) on Sunday November 10 2019, @04:57PM (#918633) Journal

          How much is the speeding ticket for going over the speed of light? :-)

          --
          The Tao of math: The numbers you can count are not the real numbers.
  • (Score: 0) by Anonymous Coward on Sunday November 10 2019, @01:44AM

    by Anonymous Coward on Sunday November 10 2019, @01:44AM (#918488)

    Those are the small ones.

  • (Score: 3, Informative) by RandomFactor on Sunday November 10 2019, @01:51AM

    by RandomFactor (3682) Subscriber Badge on Sunday November 10 2019, @01:51AM (#918490) Journal

    But neural networks, the algorithms that power such deep-learning systems, are only as good as the examples they are trained on.

    This is why they will need humans for a while yet.

    --
    В «Правде» нет известий, в «Известиях» нет правды
  • (Score: 2) by Thexalon on Sunday November 10 2019, @03:19PM (1 child)

    by Thexalon (636) on Sunday November 10 2019, @03:19PM (#918608)

    Just follow the activities of JP Morgan, Goldman Sachs, and Bank of America, and you'll have the 3 biggest sources of fraud on Wall Street.

    But I'm sure what they're after is the small-timers.

    --
    The only thing that stops a bad guy with a compiler is a good guy with a compiler.
    • (Score: 0) by Anonymous Coward on Sunday November 10 2019, @08:20PM

      by Anonymous Coward on Sunday November 10 2019, @08:20PM (#918683)

      Not sure I would call it fraud. I would call it more 'doing the needful'.

      They hire *very* junior devs then have them handling trillions of dollars. Mistakes are made. Lots of them.

      Fraud would take someone sitting down and thinking about it. You do not get that off of stackoverflow.

  • (Score: 4, Insightful) by Common Joe on Sunday November 10 2019, @08:04PM

    by Common Joe (33) <common.joe.0101NO@SPAMgmail.com> on Sunday November 10 2019, @08:04PM (#918680) Journal

    If they put in a one day delay between putting in the request to buy stocks and actually doing it, it would solve a lot of fraud problems -- more than just mentioned in the summary. In fact, slowing down the whole system would put a lot of sanity back in the stock system. But sanity and reason are no longer a goals of the stock market.

  • (Score: 0) by Anonymous Coward on Sunday November 10 2019, @08:42PM

    by Anonymous Coward on Sunday November 10 2019, @08:42PM (#918688)

    What about entities that buy call options on a relatively illiquid stock and then have someone else later buy that stock during non-trading hours when they are least liquid to inflate the price. The person/entity buying the stock ultimately takes an equity loss but the person that bought the call option makes money on the price increase and they give some of that money to the person that inflated the price.

(1)