Business Wire

Featurespace Launches Automated Deep Behavioral Networks

Share

Today, Featurespace introduces Automated Deep Behavioral Networks for the card and payments industry, providing a deeper layer of defense to protect consumers from scams, account takeover, card and payments fraud, which cost an estimated $42 billion in 2020.

"The significance of this development goes beyond the scope of addressing enterprise financial crime. It's truly the next generation of machine learning," said Dave Excell, founder of Featurespace.

The Invention

A breakthrough in deep learning technology, this invention required an entirely new way to architect and engineer machine learning platforms. Automated Deep Behavioral Networks is a new architecture based on Recurrent Neural Networks that is only available through the latest version of the ARIC™ Risk Hub.

The Challenge and the Discovery

Deep learning technology has various applications, such as in natural language processing for the prediction of the next word in a sentence, however its use in preventing fraud in card and payments fraud detection has not been optimized to protect companies and consumers from card and payments fraud. With this invention, that challenge is solved.

Transactions are intermittent, making contextual understanding of time critical to predicting behavior. Previously, building effective machine learning models for fraud prevention required data scientists to have deep domain expertise to identify and select appropriate data features - a laborious, yet vital step.

Featurespace Research developed Automated Deep Behavioral Networks to automate feature discovery and introduce memory cells with native understanding of the significance of time in transaction flows, improving upon the market-leading performance of the company's Adaptive Behavioral Analytics. Detecting fraud before the victim's money leaves the account is the best line of defense against scams, account takeover, card and payment fraud attacks. For the following groups, the benefits of Automatic Deep Behavioral Networks include:

Consumers:

  • Enabling genuine transactions with reduced verification; and
  • Automatically identifying scams, account takeover, card and payment fraud attacks before the victim's money leaves the account.

Data scientists:

  • Automatically discovering features in transaction events;
  • Pushing machine learning logic through the entire modelling stack;
  • Leveraging the irregularity of human actions to identify anomalistic behavior; and
  • Retaining all of the discoveries of Featurespace's Adaptive Behavioral Analytics.

Card and Payments Industry:

  • Improving risk score certainty across all transactions (fraud detection during the transaction is increased and genuine behavior is more accurately identified to facilitate the acceptance of more transactions);
  • Providing performance uplift for all payment types, including card and ACH/BACS, wire, P2P and faster payments;
  • Improving the detection of high-value, low-volume fraud (and also detection of low-value, high-volume fraud);
  • Reducing step-up authentication;
  • Providing strict model governance documentation, with explainable logic, fair decision making and reason codes; and
  • Delivering stable, real-time scoring with high throughput and low latency response times for business-critical enterprises, even under surge conditions.

Excell continued, “As real-time payments, digital transformation and consumer demand require the instantaneous movement of money, our role is to ensure the industry has the best tools for protecting their organizations and consumers from financial crime. I am immensely proud of our research team and their dedication to machine learning innovation on behalf of our customers.”

About Featurespace – www.featurespace.com

Featurespace™ is the world leader in Enterprise Financial Crime prevention for fraud and Anti-Money Laundering. Featurespace invented Adaptive Behavioral Analytics and Automated Deep Behavioral Networks, both of which are available through the ARIC™ platform, a real-time machine learning software that risk scores events in more than 180 countries to prevent fraud and financial crime.

ARIC™ Risk Hub uses advanced, explainable anomaly detection to enable financial institutions to automatically identify risk, catch new fraud attacks and identify suspicious activity in real-time. More than 30 major global financial institutions are using ARIC to protect their business and their customers. Publicly announced customers include HSBC, TSYS, Worldpay, NatWest Group, Contis, Danske Bank, ClearBank, AK Bank and Permanent TSB.

Contact information

Michael Touchton, Featurespace
PR and Communications Manager
Michael.touchton@featurespace.com
+1 (423) 364-5491

About Business Wire

Business Wire
Business Wire



Subscribe to releases from Business Wire

Subscribe to all the latest releases from Business Wire by registering your e-mail address below. You can unsubscribe at any time.

Latest releases from Business Wire

New F1 Insights Powered by AWS Will Help FORMULA 1 Fans Make Sense of Split-Second Decisions on the Track15.4.2021 09:30:00 CEST | Press release

Today, Amazon Web Services (AWS), an Amazon.com, Inc. company (NASDAQ: AMZN), and FORMULA 1 (F1) (NASDAQ: FWONA, FWONK) are introducing six new F1 Insights powered by AWS that will roll out through the 2021 racing season. The new additions mean a total of 18 AWS-powered stats will be available to fans by the end of the season. F1 Insights powered by AWS are real-time racing statistics, displayed as on-screen graphics, that transform the fan experience before, during, and after each race by providing the data and analysis fans need to interpret driver and team race strategy and performance. The first new stat, Braking Performance, will debut at the GRAND PRIX in Italy, April 16-18. The new set of statistics for 2021 will use a range of AWS technologies, including machine learning, to help fans better understand and highlight potential race outcomes and compare their favorite drivers and cars.For more information about AWS and its involvement with F1, including the 12 previously released

Peter Windisch Appointed Chief Technology Officer at Excelya15.4.2021 09:03:00 CEST | Press release

Today, Excelya, the leading European contract research organization, has announced the appointment of Peter Windisch to the position of Chief Technology Officer (CTO). As CTO, Peter will aim to leverage data and technology to further optimize its client offer. He will be made a member of the Executive Committee and will be based in Germany. Peter was most recently VP of Operations and Client Partner at PRA Health Sciences and has worked for decades in various leadership positions in health and technology. He began his career in health as a Manager of Information Technology and Data Management before moving up the ranks to Managing Director of various regions in Europe at IMEREM (now part of PRA Health Sciences) and ReSearch Pharmaceutical Services. Alan Morgan, CEO of Excelya: “Excelya is investing heavily in technology to better support our clients and patients for the trials that we are managing. Innovation and efficiency are at the heart of what we do. This new position recognizes t

Completion of the Third Clinical Trial - an Important Achievement for Medicortex Finland15.4.2021 08:25:00 CEST | Press release

Medicortex Finland Oy, a biotechnology company developing a breakthrough biomarker-based diagnostic kit for brain injury detection, completed collection of body fluid samples in its third large clinical study. Children and adolescents were recruited who visited the hospital with a suspected mild traumatic brain injury or concussion. "Collecting the samples in this large clinical trial is a significant achievement for Medicortex, and represents an important step forward in the development of the ProbTBITM, a diagnostic kit for early detection of head injury" said Dr. Adrian Harel, Chief Executive Officer of Medicortex Finland. "Brain injury is a devastating condition leading to medical complications if not diagnosed. We have the opportunity to develop a portable non-invasive test for quick detection of mild traumatic brain injury (TBI) and concussion, and thereby help young patients and families who so desperately need it.” Dr. Harel added. In the current clinical study Medicortex colle

Valbiotis: Largely Successful Capital Increase Through a Private Placement Totaling 15 Million Euros15.4.2021 07:35:00 CEST | Press release

Regulatory News: Valbiotis (Paris:ALVAL) (FR0013254851 – ALVAL, PEA-PME eligible), a Research & Development company committed to scientific innovation for the treatment and prevention of metabolic diseases, today announces the large successful capital increase through a private placement open to certain categories of beneficiaries launched the previous day and achieved using an accelerated bookbuilding process. Given the very high demand from French and international investors, Valbiotis decided to set the amount of the capital increase at 15 million euros, compared to approximately 12 million euros initially forecast. Sébastien PELTIER, CEO of Valbiotis stated: "I am extremely grateful to all the new investors who participated in this capital increase, as well as all our historic shareholders who continue to support our company in its mission and its development. This capital increase is key, as it will enable us to accelerate our development program for the prevention of high blood p

ABB Issues Trading Update Following Better-Than-Anticipated Performance in Q115.4.2021 06:46:00 CEST | Press release

ABB is publishing preliminary information on its first-quarter 2021 results, which according to the information available to the company, is better than the latest company guidance and current market consensus. The preliminary results were driven by a stronger-than-anticipated market development, especially during the last weeks of March, and relates primarily to the short-cycle business. Quarterly demand is likely to have been supported by customer stock-building activities related to both component availability constraints and rising commodity prices in the industry. Preliminary results for first quarter 2021: ($ millions, unless otherwise indicated) Change Q1 2021 Q1 2020 US$ Comparable1 Orders ~7,750 7,346 ~+6% ~+1% Revenues ~6,900 6,216 ~+11% ~+7% Operational EBITA2, % ~13.5% 10.2% ~+330 pts On the back of recent market developments, ABB is raising its revenue guidance for full year 2021 outlook and now anticipates comparable revenue growth of ~5% or higher (previously: comparable

Mattel Unveils First-of-its-Kind, CarbonNeutral ® Matchbox ® Tesla Roadster Die-cast Vehicle Made from 99% Recycled Materials to Serve as Brand Blueprint15.4.2021 06:01:00 CEST | Press release

Today, Mattel, Inc. (NASDAQ: MAT) announced Drive Toward a Better Future, its product roadmap to make all Matchbox die-cast cars, playsets and packaging with 100% recycled, recyclable or bio-based plastic by 2030. This is in line with Mattel’s goal to achieve 100% recycled, recyclable or bio-based plastic materials across all its products and packaging by 2030. This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20210414006005/en/ Mattel is unveiling the Matchbox Tesla Roadster, its first die-cast vehicle made from 99% recycled materials and certified CarbonNeutral®*. The Matchbox Tesla Roadster will be available starting in 2022. (Photo: Business Wire) To illustrate these principles, Mattel is unveiling the Matchbox TeslaRoadster, its first die-cast vehicle made from 99% recycled materials and certified CarbonNeutral®*. The Matchbox Tesla Roadster will be available starting in 2022. The reimagined broader Matchbox brand includes n

imc Test & Measurement Joins Battery Ventures’ Test and Measurement Platform15.4.2021 06:01:00 CEST | Press release

Battery Ventures, a global, technology-focused investment firm, has reached an agreement to acquire imc Test & Measurement (“imc”), a global provider of productive test and measurement hardware and software solutions. Joining Battery’s group of companies in the test and measurement market, imc will operate alongside U.S.-based Audio Precision and Denmark-based GRAS Sound & Vibration, which were acquired by Battery in 2018 and 2020, respectively. Terms of the transaction were not disclosed. Founded in 1988, imc is a well-known provider of state-of-the-art data acquisition systems and software. The company serves customers in markets such as automotive, energy, rail and aerospace, among others. In partnership with Battery, Audio Precision and GRAS, imc will continue its long-standing tradition of pursuing growth across the sectors it serves. Joining forces with Audio Precision and GRAS, imc will benefit from business synergies across the group of companies and drive its future growth thr

In our pressroom you can read all our latest releases, find our press contacts, images, documents and other relevant information about us.

Visit our pressroom