Arabic Arabic Chinese (Simplified) Chinese (Simplified) Dutch Dutch English English French French German German Italian Italian Portuguese Portuguese Russian Russian Spanish Spanish
0

FICO (FICO) Granted Eleven New Patents in Fraud, AI/ML, and Digital Decisioning | #phishing | #scams | #hacking | #aihp



Get inside Wall Street with StreetInsider Premium. Claim your 1-week free trial here.


Highlights:

  • FICO has been awarded eleven new patents in fraud, AI/ML, and digital decisioning
  • FICO holds 208 active US and foreign patents to date
  • FICO currently has 83 pending patent applications

Leading analytics software firm FICO has been granted eleven new patents over the last eight months related to fraud, artificial intelligence (AI)/machine learning (ML), and digital decisioning. With these grants FICO’s patent portfolio now totals 208 active patents, with 83 additional applications filed and pending. The latest eleven patents awarded focus on ethical artificial intelligence, machine learning, and other analytics technologies used by FICO to help its customers build responsible and effective AI decisioning systems leveraging purpose-built AI and ML algorithms.

“FICO is a leading AI innovator, and this is reflected by the fact that we continuously file for new patents in this space,” said Scott Zoldi, chief analytics officer at FICO. “Our focus is to pioneer the use of responsible artificial intelligence and correct operationalization in decisioning systems. Our newly granted patents include a variety of software solutions, fraud analytics, enhanced machine learning algorithms, and our continued focus on behavioral and transaction analytics.”

FICO’s newly awarded patents include:

  • “Entity Resolution Based On Character String Frequency Analysis,” which covers techniques for generating similarity scores between one or more pairs of character strings based on degrees of commonality or rarity. It is a feature in FICO® Identity Resolution Engine.
  • “Advanced Learning System for Detection and Prevention of Money Laundering,” which relates to detecting risky entity behavior using an efficient frequent behavior-sorted list and generating threat scores that may be applied within the context of anti-money laundering (AML) and retail banking fraud detection systems. This technology is incorporated into FICO® Siron® Anti-Financial Crime Solutions.
  • “Configuration Packages for Software Products,” which covers configuration software innovations, including the configuration of pre-compiled code frameworks. This technology is in FICO® Strategy Director and FICO® Studio, both part of FICO® Platform.
  • “Visualization for Payment Card Transaction Fraud Analysis,” which relates to a computer-implemented method and system for visualizing card transaction fraud analysis. The visualization techniques of this patent enable domain-specific interfaces that can help fraud analysts make better decisions quickly and easily. This technology is incorporated into FICO® Falcon® Fraud Manager.
  • “False Positive Reduction in Abnormality Detection System Models,” which covers technology for reducing the false-positive rate for abnormalities for transactions occurring at the same merchant and/or location where a consumer has transacted previously. Conversely, the detection rate of actual fraud transactions that occur while a transaction entity is experiencing fraud is improved. This is an important part of FICO® Falcon® Platform-based cloud enhanced analytics and improvements to in-stream analytics.
  • “Temporal Explanations of Machine Learning Model Outcomes,” which describes a system and method for identifying and isolating relevant past transactions that led to an ultimate decision in an AI transactional analytics system, for providing meaningful explanations in transaction systems such as stopping payment card fraud, detecting cyber security threats, credit risk, and identifying money laundering activities.
  • “High Resolution Transaction-level Fraud Detection for Payment Cards in a Potential State of Fraud,” which covers a system and method to distinguish fraudulent transactions from legitimate transactions, when the payment card used is in a state of fraud, using a specialized algorithm referred to as a pinpoint model. This innovation is important to FICO’s customer communications offerings and adaptive analytic initiatives in FICO® Falcon® Fraud Manager.
  • “Method and Apparatus for Analyzing Coverage, Bias, and Model Explanations in Large Dimensional Modeling Data,” which relates to exposing weak data coverage and potential biases within a dataset, particularly large multi-dimensional datasets. This is relevant to enabling humble AI strategies and has been used in FICO® Falcon® Fraud Manager and FICO® Member Score models.
  • “Data Distillery for Signal Detection,” which claims systems and methods for data analytics and discovery of patterns or signals in large volumes of data for potential use in decisioning.
  • “Generating Optimal Strategy for Providing Offers,” which relates to generating strategies to provide high quality offers to customers that require minimal, negligible, or no manual expertise by analysts and domain experts, thereby reducing time, effort, and cost.
  • “Distributed Data Processing Framework,” which covers a system and method for multi-level data aggregation, data filtering, and data input generation from raw transaction level data. These innovations address the inadequacy of traditional data processing applications in handling exceptionally voluminous and/or complex data sets.

Serious News for Serious Traders! Try StreetInsider.com Premium Free!


You May Also Be Interested In

Click Here For The Original Source.


————————————————————————————-

National Cyber Security

FREE
VIEW