18605541. FRAUD DETECTION IN CONTACT CENTERS USING DEEP LEARNING MODEL simplified abstract (Wells Fargo Bank, N.A.)
Contents
FRAUD DETECTION IN CONTACT CENTERS USING DEEP LEARNING MODEL
Organization Name
Inventor(s)
Nick A. Maiorana of Charlotte NC (US)
Judy Cantor of Tinton Falls NJ (US)
Kevin R. Cieslak of Novato CA (US)
David Gorlesky of Concord NC (US)
Jeremy Ernst of Waxhaw NC (US)
FRAUD DETECTION IN CONTACT CENTERS USING DEEP LEARNING MODEL - A simplified explanation of the abstract
This abstract first appeared for US patent application 18605541 titled 'FRAUD DETECTION IN CONTACT CENTERS USING DEEP LEARNING MODEL
The abstract describes a method that involves analyzing data from calls into an interactive voice response (IVR) system to determine the likelihood of fraudulent activity during the call.
- Receiving data from a user device about actions taken within the IVR system and results produced by the IVR system during the call.
- Converting the actions and results into code pairs using a dictionary based on training data.
- Determining an activity pattern during the call based on the sequence of code pairs.
- Calculating the probability of fraudulent activity during the call based on the activity pattern.
Potential Applications: - Fraud detection in IVR systems - Enhancing security in call centers - Improving customer authentication processes
Problems Solved: - Identifying fraudulent activity in real-time - Enhancing overall security measures in IVR systems
Benefits: - Increased protection against fraudulent activities - Improved customer trust and satisfaction - Streamlined fraud detection processes
Commercial Applications: Title: "Enhancing Security in IVR Systems: A Fraud Detection Method" This technology can be utilized by call centers, financial institutions, and other organizations that rely on IVR systems to enhance security and prevent fraudulent activities.
Questions about the technology: 1. How does this method compare to traditional fraud detection techniques used in IVR systems? 2. What are the potential limitations of this technology in detecting sophisticated fraudulent activities?
Original Abstract Submitted
An example method is described. The method includes receiving, by a computing system, data indicative of a call into an interactive voice response (IVR) system from a user device and determining, by the computing system and based on the data, a set of actions performed by the user device within the IVR system and a corresponding set of results performed by the IVR system during the call. Additionally, the method includes converting, by the computing system, the set of actions and the corresponding set of results into a sequence of code pairs using a dictionary established based on training data, determining, by the computing system, an activity pattern during the call based on the sequence of code pairs; and calculating, by the computing system, a probability that the call is fraudulent based on the activity pattern during the call.
