Amazon Policeware: Fraud Detection

August 4, 2020

We spotted “Fraud Detector Launched on AWS Platform.” As one pre pandemic, face-to-face conference organizer told me, “No one cares about Amazon policeware. The future is quantum computing.”

Yeah, okay.

Amazon does not buy big booths at law enforcement and intelligence conferences. For now, that’s the responsibility of its partners. No booth, no attention at least for one super charged quantum cheerleader.

The write up states:

With Amazon Fraud Detector, customers use their historical data of both fraudulent and legitimate transactions to build, train, and deploy machine learning models that provide real-time, low-latency fraud risk predictions. To get started, customers upload historical event data (e.g. transactions, account registrations, loyalty points redemptions, etc.) to Amazon Simple Storage Service (Amazon S3), where it is encrypted in transit and at rest and used to customize the model’s training. Customers only need to provide any two attributes associated with an event (e.g. logins, new account creation, etc.) and can optionally add other data (e.g. billing address or phone number). Based upon the type of fraud customers want to predict, Amazon Fraud Detector will pre-process the data, select an algorithm, and train a model.

And what does an Amazon person whom remains within the Amazon box with the smile on the side say? The write up reports:

Customers of all sizes and across all industries have told us they spend a lot of time and effort trying to decrease the amount of fraud occurring on their websites and applications. By leveraging 20 years of experience detecting fraud coupled with powerful machine learning technology, we’re excited to bring customers Amazon Fraud Detector so they can automatically detect potential fraud, save time and money, and improve customer experiences—with no machine learning experience required.

Several observations:

  1. Combined with “other” financial data available within the AWS system, Amazon’s fraud detection system may be of interest to some significant financial services firms.
  2. The technology provides a glimpse of what AWS can support; for example, matching tax returns to “other” financial signals in order to flag interesting returns.
  3. The technical widgets in the AWS structure makes it possible for a clever partner to reinvent a mostly unknown financial task: Identification or flagging of medical financial data for fraud. Subrogation with the point-and-click Amazon interface? Maybe.

To sum up, we offer a one hour lecture about Amazon’s policeware initiative. I know “free” is compelling, but this lecture costs money. For details write darkcyber333 at yandex dot com. Note: The program is different from our Amazon lecture for the 2020 US National Cyber Crime Conference.

No, it is not about the Quantum Computer Revolutions, but we do discuss Amazon’s Quantum Ledger Database. It works. Some quantum computing demonstrations do not.

Stephen E Arnold, August 4, 2020


Comments are closed.

  • Archives

  • Recent Posts

  • Meta