FICO Awarded 13 New Patents for Responsible AI, Fraud and Decision Management

  • Artificial Intelligence , Security
  • 30.06.2020 12:31 pm

Silicon Valley analytic software firm FICO has been awarded 13 new patents related to fraud, artificial intelligence (AI) and decision management. In total, FICO currently holds 198 US and foreign patents and 103 pending patent applications.

Five of the patents are for ground-breaking analytic technology used by FICO’s industry-leading FICO® Falcon® Platform for fraud management:

  • Cloud Process for Rapid Data Investigation and Data Integrity Analysis, a patent now granted in France, Germany and the UK, relates to the FICO® Falcon® Intelligence Network and FICO® Falcon® Platform Cloud Edition.  Superior fraud detection is achieved by analyzing an abundance of transactional data in order to effectively understand behavior and assess risk, at an individual level. This new patent helps improve the speed and quality of the data being analyzed.
  • Real Time Autonomous Archetype Outlier Analytics covers a method and system for identifying subsets of transactions. This new patent identifies transactions that generate anomalies in behavioral archetypes and alerting in a score. This innovation is utilized in FICO financial crime models to detect fraud and money laundering with pinpoint accuracy. FICO® Siron® AML and FICO® Falcon® Platform use these models.
  • False Positive Reduction in Abnormality Detection System Models. This invention achieves false positive reduction in transactions with recurrences in a consumer’s previous transaction history. This innovation further identifies non-fraud transactions that occur during a fraud episode, thereby improving the customer experience. This is an important part of our approach to improve in-stream analytics with the FICO® Falcon® Platform.
  • Auto Adaptive Anomaly Detection System for Streams identifies click fraud in connection with Internet search engine advertising. 
  • Adaptive Fraud Detection relates to a real-time adaptive system for fraud detection implementing automatic binning, feature selection, adaptive statistical models, and score blending. The adaptive technology overlays core machine learning technology to adjust to near-term fraud and non-fraud activity occurring between model retrains.  This technology is a critical component of machine learning models within the FICO® Falcon® Platform.

FICO inventors also received patents related to analytics and decision management:

  • Cloud-Based Decision Management Platform covers a cloud-based platform for providing analytic decision services. This innovation is core to the FICO® Decision Management Platform and FICO® Analytic Cloud offerings.
  • Efficient Storage and Retrieval of XML Data relates to a computing server that can efficiently store data of an Extensible Markup Language (XML) document in a data store, and retrieve, when required, the stored data from the data store within a constant amount of time, independent of the number of XML documents in the data store. This technology is used in FICO® Origination Manager.
  • Dynamic Business Rule Creation Using Scored Segments relates to a method of extracting sentiment and opinion from data streams for use in decision strategies.
  • Building Resilient Models to Address Dynamic Customer Data Use Rights relates to building analytic models and utilizing those models in production while addressing dynamic customer data use rights.  The innovation can also address other scenarios that necessitate withdrawal of data that had been used to build an existing model. 
  • System and Method for Round Trip Engineering of Decision Metaphors relates to a testing framework associated with a decision engine to profile decision metaphors such as decision tables, decision trees, scorecards and, based on the profile, automatically generate test data to test these metaphors. With the new patent, the testing framework automates the generation of test data for complex decision service projects. This technology is used in FICO® Origination Manager.
  • Method and Apparatus for Reconciliation of Multiple Sets of Data reconciles records from many data sources to identify discrepancies. It can be helpful in a variety of industries for uses such as revenue assurance, where it can identify discrepancies that would lead to revenue leakage or over-billing of a service.

“We are innovators pushing the envelope of analytics,” said Scott Zoldi, chief analytics officer, FICO.  “Being at the forefront of AI and intelligent decision automation is not only the key to our success but that of our customers.”

“Our products and services make the day-to-day working lives and decision making in global banks, airlines, telecoms and energy providers simpler, easier and more profitable,” added Nikhil Behl, chief marketing officer at FICO.

Related News