Siamese Network Credit Card Number Matching

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing systems face challenges in accurately matching new credit card numbers with old credit card numbers for the same account, especially when the old credit card number changes due to expiration, loss, theft, or upgrade, without accessing the account holder's personal information.

Innovation Solution

A computing device utilizes machine learning, specifically a modified siamese network and transformer models, to match old and new credit card numbers based on transactional history, without requiring access to the account holder's personal information. The device processes transactional data, clusters new credit card numbers associated with old ones, and uses image-like data formats and neural networks to determine continuation matches.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the credit card company accesses the account holder's personal information to link new and old credit card numbers, then the matching accuracy improves, but customer privacy is compromised

Engineering Contradiction:
Improvematching accuracyVSAvoidcustomer privacy concern
Core Design Contradiction:
Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The patent introduces ABU (Automatic Billing Update) information as an intermediary that indirectly links old and new credit card numbers without requiring direct access to account holder's personal information. The ABU information serves as a mediator that contains the relationship between old and new card numbers while preserving customer privacy, allowing the credit card company to perform matching without viewing sensitive account data.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If the credit card company manually tracks and matches credit card number changes, then matching accuracy improves, but the complexity and cost of operations increase

Engineering Contradiction:
Improvematching accuracyVSAvoidoperational complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system implements automatic detection and matching of credit card number changes through the ABU information mechanism. Instead of requiring manual intervention to track and match card number changes, the system automatically processes the ABU information that is already generated during billing operations, allowing the matching function to serve itself without additional operational complexity.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The ABU information serves multiple functions simultaneously: it enables automatic billing updates, provides the link between old and new credit card numbers for matching purposes, and maintains customer privacy. This multi-functionality eliminates the need for separate manual tracking systems, reducing operational complexity while maintaining matching accuracy.

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

3Ease of operation

If the issuer provides ABU information to the credit card company, then the matching process becomes easier, but information security risks increase

Engineering Contradiction:
Improvematching easeVSAvoidinformation security risk
Core Design Contradiction:
Ease of operationVSObject-affected harmful factors

Solution Approach 1:

The patent applies local quality by providing ABU information selectively and specifically for matching purposes only. The ABU information contains precisely the data needed for matching (the relationship between old and new card numbers) without including broader account holder personal information. This localized information provision enables easy matching while minimizing information security risks by limiting the scope of shared data to only what is necessary.

Inventive Principle:
Principle #3Local quality

Data Source

PatentUS20250139711A1Method to determine that a credit card number change has occurred
Publication Date: 2025.05.01 MASTERCARD INT INC
  • US20250139711A1 patent drawing
  • US20250139711A1 patent drawing
  • US20250139711A1 patent drawing

AI summary

A computing device for determining a new credit card number that is a continuation match with an old credit card number of a credit card account that has changed numbers comprises a processing element programmed to: receive transactional data for a plurality of credit card numbers, determine a plurality of old credit card numbers and a plurality of new credit card numbers, determine a plurality of clusters of new credit card numbers, convert the transactional data for each old credit card number and the associated cluster of new credit card numbers into snapshots with an image-like data format, train a modified siamese network with instances of snapshots of an old credit card number, a first new credit card number, and a second new credit card number, and use the modified siamese network to determine one new credit card number that is an upgrade of one old credit card number.