Blockchain Transaction Linking for Fraud Risk Model Training
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Public blockchain data lacks significant insight for individual and community evaluation due to transactor anonymity, limiting its effectiveness in training machine learning models for fraud risk and community tendencies.
Innovation Solution
Integrate public blockchain data with private domain data to train machine learning models, using digital wallet services to associate transactions with specific entities, and enhance models with user-to-user associations derived from public blockchain information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If public blockchain data is used for machine learning training, then data availability and decentralization are improved, but measurement precision and reliability deteriorate due to transactor anonymity
Solution Approach 1:
The patent introduces digital wallet services as an intermediary layer between public blockchain data and machine learning models. The wallet service acts as a mediator that receives anonymous blockchain transactions, associates them with identifiable user accounts through its private domain data, and provides enriched transaction data to the machine learning system. This intermediary resolves the contradiction by preserving data availability from the public blockchain while adding the precision of user identification through the wallet service's association mechanisms.
2Reliability
If transactor anonymity is maintained in public blockchain, then decentralization and security are improved, but loss of information increases regarding user identity and transaction context
Solution Approach 1:
The patent segments the information system into three distinct layers: the public blockchain layer that maintains anonymous transaction records for integrity, the digital wallet service layer that bridges anonymous and identified data, and the machine learning application layer that consumes enriched data. This segmentation allows each layer to fulfill its specific function - the blockchain maintains anonymity and integrity, while the wallet service recovers user identity information without compromising the blockchain's security model.
3Device complexity
If public blockchain data is used directly for fraud detection, then system complexity is reduced, but measurement precision deteriorates due to lack of user associations
Solution Approach 1:
The digital wallet service functions as a crucial intermediary that enriches anonymous blockchain transactions with user identity information, account histories, and contextual data. This intermediary layer enables fraud detection models to access both the simplicity of public blockchain data and the precision of user-specific information, resolving the contradiction between system simplicity and detection accuracy.
Data Source
AI summary
A computer-implemented method includes collecting information respective of one or more transactions stored on a public blockchain, determining that a first private account hosted by the computing system is associated with a first transaction of the one or more transactions, determining that a second private account hosted by the computing system is associated with a second transaction of the one or more transactions, associating the first private account with the second private account based on a connection of the first transaction to the second transaction on the public blockchain, and training a machine learning model according to the association of the first private account with the second private account.