Digital Wallet Fraud Scoring for Payment Authentication
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current payment card transaction systems face challenges such as high network load, fraudulent transactions, consumer inconvenience, transaction abandonment, unavailability of customizable fraud services, increased risk for merchants, and limited data access for issuers, particularly in card-not-present transactions.
Innovation Solution
A risk-based decisioning system that evaluates payment card transactions by identifying fraud features from digital wallets, computing fraud scores, and providing these scores for authentication, thereby reducing unnecessary step-up challenges and enhancing fraud detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional authentication protocols are used for payment card transactions, then fraud detection capability is limited, but network load increases and consumer inconvenience increases due to unnecessary step-up challenges
Solution Approach 1:
The system performs preliminary fraud risk assessment by analyzing fraud feature data from digital wallets before initiating authentication. This preliminary action identifies low-risk transactions that can bypass step-up challenges, reducing network load while maintaining fraud detection capability for high-risk transactions
Solution Approach 2:
The system changes the parameter of authentication requirement based on computed fraud scores. Transactions with low fraud scores receive standard authentication treatment, while high fraud score transactions trigger step-up challenges. This dynamic parameter adjustment optimizes network load by eliminating unnecessary authentication steps
2Reliability
If traditional authentication protocols are used for payment card transactions, then fraud detection capability is limited, but consumer inconvenience increases due to unnecessary step-up challenges
Solution Approach 1:
The system dynamically adjusts authentication requirements based on fraud risk parameters. Consumers with low-risk transaction profiles experience streamlined authentication, while high-risk transactions trigger additional verification steps. This resolves the contradiction by making the system adaptive rather than uniformly restrictive
Solution Approach 2:
The system replaces mechanical step-up challenges with data-driven fraud scoring based on digital wallet analysis. Instead of automatically requiring additional authentication, the system uses computational fraud assessment to determine when challenges are necessary, reducing consumer inconvenience while maintaining security
3Measurement precision
If fraud feature data is collected and analyzed from digital wallets, then fraud detection accuracy improves, but data access requirements increase for issuers
Solution Approach 1:
The system introduces an intermediary layer that collects fraud feature data from digital wallets and processes it through standardized protocols. This intermediary handles data access requirements, transforming raw wallet data into structured fraud scores that issuers can access without direct wallet access, thus improving detection accuracy while managing data access complexity
Solution Approach 2:
The system segments fraud detection into distinct components: digital wallet data collection, fraud feature extraction, score computation, and issuer decision-making. This segmentation allows each component to handle specific data requirements independently, improving overall detection accuracy while managing data access requirements through modular architecture
Data Source
AI summary
A computing device for risk-based analysis of a payment card transaction is provided herein. The computing device includes a processor communicatively coupled to a memory. The computing device is programmed to receive a request for authentication of the payment card transaction. The payment card transaction includes a suspect consumer presenting a payment card from a digital wallet of a privileged cardholder. The computing device is also programmed to identify fraud feature data from the digital wallet. The computing device is further programmed to compute a fraud score for the payment card transaction based at least in part on the fraud feature data. The computing device is still further programmed to provide the fraud score for use during authentication of the suspect consumer.


