CNP Fraud Detection via Interchange Network Scoring

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Online merchants face challenges in detecting sophisticated fraud attempts in card-not-present transactions due to limited access to the total cardholder history across multiple merchants, leading to increased costs and revenue loss.

Innovation Solution

A computer system and method for fraud detection in card-not-present transactions that includes a network host site and an interchange network, which receives a transaction authorization request, performs real-time fraud risk scoring using defined models, and updates card account profiles with current transaction data to calculate and transmit a fraud risk score, enabling merchants to make informed authorization decisions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If merchants use automated screening services or manual review to detect fraud, then fraud detection capability is improved, but operational costs and processing time increase

Engineering Contradiction:
Improvefraud detection capabilityVSAvoidoperational complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent introduces an intermediary fraud detection system that sits between the merchant and the payment processor. This system automatically analyzes transaction data, device information, and behavioral patterns to generate fraud risk scores, eliminating the need for merchants to implement complex manual review processes while maintaining high detection capability.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The fraud detection system performs self-service by automatically collecting data from multiple sources, analyzing risk patterns, and making authorization decisions without requiring merchant intervention. The system continuously learns from new data and adjusts its detection algorithms autonomously.

Inventive Principle:
Principle #25Self-service

2Measurement precision

If merchants implement comprehensive fraud detection tools, then fraud detection precision is improved, but system complexity and implementation difficulty increase

Engineering Contradiction:
Improvefraud detection precisionVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent creates a universal fraud detection platform that serves multiple functions: analyzing transaction data, evaluating device fingerprints, assessing behavioral patterns, and generating risk scores. This multi-functional system consolidates what would otherwise require multiple separate tools into a single integrated solution.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The fraud detection system segments the analysis into distinct modules: transaction data analysis, device fingerprinting, behavioral pattern recognition, and risk scoring. Each module handles a specific aspect of fraud detection, making the overall complex system manageable and easier to implement.

Inventive Principle:
Principle #1Segmentation

3Reliability

If merchants access only their own site's cardholder history, then data privacy is maintained, but fraud detection accuracy deteriorates due to limited view

Engineering Contradiction:
Improvefraud detection accuracyVSAvoidinformation availability
Core Design Contradiction:
ReliabilityVSLoss of information

Solution Approach 1:

The patent merges data from multiple merchants and payment processors into a centralized fraud detection system. By combining transaction histories, device fingerprints, and behavioral patterns from across the network, the system achieves comprehensive fraud detection accuracy while maintaining data privacy through controlled access and aggregation.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentUS20210012345A9Method and system for determining fraud in a card-not-present transaction
Publication Date: 2021.01.14 MASTERCARD INT INC
  • US20210012345A9 patent drawing
  • US20210012345A9 patent drawing
  • US20210012345A9 patent drawing

AI summary

A computer system for fraud detection associated with a card-not-present payment card system is provided. The system includes a network host site and an interchange network including a processor communicatively coupled to a memory device for storing data and to the network host site wherein the processor is programmed to receive a card transaction authorization request message from a merchant, route the card transaction authorization request to the network host site to perform CNP fraud risk scoring, and based on the criteria of the card transaction authorization request, call at least one of a plurality of fraud scoring models defined for criteria of the transaction authorization request. The processor is further programmed to calculate the fraud risk score based on the current transaction authorization request data and an updated card account profile, and transmit the message to an issuer of the payment card for approval of the request.