FICO Continues to Drive Innovation with 13 New Patents for AI, Machine Learning, Fraud and Decision Management Platform

0

SAN JOSE, California, August 6, 2021 / PRNewswire / –

Strong points:

  • FICO Obtained 13 New Patents For Fraud, AI / ML And Decision Management Platforms
  • FICO now holds 204 U.S. and foreign patents
  • FICO currently has 85 pending patent applications

Leading digital decision-making platform company, FICO, today announced that it has secured 13 new patents related to artificial intelligence (AI), machine learning (ML), fraud and decision management platform . With the latest patents, FICO continues to help clients digitally transform their businesses by automating key business processes and decision making with cutting-edge innovations.

With the 13 new innovations, FICO now holds 204 U.S. and foreign patents and 85 pending patent applications. FICO has pioneered several industry-changing innovations in artificial intelligence, machine learning, and other analytical methods. FICO’s rich portfolio of analytics and fraud solutions help clients deal with ever-increasing volumes and variety of data across the enterprise, as well as protect businesses from the latest fraud in real time .

“FICO provides our clients with the solutions they need, when they need them, and driving their success forward is what allows us to thrive as an organization. We have created and nurtured an environment that allows me and my colleagues to push the boundaries and continue to drive innovations that help clients succeed. It is exciting to see our work receiving this recognition, ”said Scott Zoldi, Director of Analysis, FICO.

The patents awarded to FICO and their innovative leaders include:

  • “Explain machine learning models by latent behavioral characteristics followed” by Scott Zoldi. This invention is a system and method for explaining the behavior of a machine learning model, which can benefit not only those seeking to meet regulatory requirements when using models, but also help guide users. models to assess and increase the robustness associated with model governance processes. This innovation is used in the FICO® Falcon® Fraud Manager and FICO® Falcon® X models.
  • “Quick automatic explanation of noted observations.” This patent Gerald Fahner and Scott Zoldi relates to systems and methods for generating concise explanations of scored observations that achieve computational good and efficient trade-offs between ranking performance and explainability of scored observations, based on a framework of partial dependency functions (PDF), Multilayer Neural Networks (MNN) and Latent Explanations Neural Network Scoring (LENNS).
  • “Detection of merchant, ATM and network compromise.” This patent Scott Zoldi relates to the generation of compromise profiles for merchants and financial accounts based on a comparison of reported fraud data with an account profile, an account transaction profile, a merchant device profile and a user profile. ‘Merchant Device Account History – to quickly identify when and when account information was obtained by an unauthorized third party. The systems and methods claimed by the patent relate to FICO offerings for the detection of points of compromise and mass compromise.
  • “System and method for linearizing messages from data sources for optimized high performance processing in a stream processing system.” This innovation of Chalini Raghavan and Tom traugher concerns the processing of data objects by a distributed flow computer system, and more precisely, the linearized processing of data objects. This technology is integrated into FICO® Decision Management Platform Streaming.
  • Multilayer Self-Calibration Assays “, an invention of Scott Zoldi features multi-layered, self-calibrated analyzes to detect fraud in transaction data without substantial historical data, including limited or no outcome data. In markets where historical transaction data is not widely available, this invention enables adaptive selection and grouping of variables relating to real-time transaction data, for processing by a number of self-calibration models. independent. The outputs of these models are combined for an accurate fraud score based on the detection of anomalies of the hidden latent features discovered.
  • “Detection of behavioral misalignment within hard entity segmentation using archetype grouping” by Scott Zoldi and Joe murray. This invention is an automated way to learn archetypes that capture many aspects of an entity’s behavior, and to assign entities to a mixture of archetypes, so that each entity is represented as a distribution on several archetypes. Considering these representations in archetypes, abnormal behavior can be detected by finding misalignment with a plurality of entities having grouping of archetypes in hard segmentation. FICO® Anti-Financial Crime Solutions uses this technology.

In the past 12 months, FICO has been named a leader in digital decision-making as well as a leader in innovation, AI applications and corporate financial crime and fraud by leading analyst firms. plan.

About FICO
FICO (NYSE: FICO) makes decisions that help people and businesses around the world thrive. Founded in 1956 and headquartered in Silicon Valley, the company is a pioneer in the use of predictive analytics and data science to improve operational decisions. FICO holds more than 200 U.S. and foreign patents on technologies that increase profitability, customer satisfaction, and growth for companies in financial services, telecommunications, healthcare, retail and many other industries. . Using FICO solutions, businesses in more than 120 countries are doing everything from protecting 2.6 billion payment cards from fraud, to helping people get credit, to ensuring that millions of planes and rental cars are in the right place at the right time.

Learn more about https://www.fico.com

FICO and Falcon are registered trademarks of Fair Isaac Corporation in the United States and other countries.

FICO SOURCE

Related links

https://www.fico.com


Source link

Leave A Reply

Your email address will not be published.