Blockchain Collaborative Analytics for Fraud Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for detecting fraud in bank deposit operations are inadequate in terms of speed and adaptability, as they rely on outdated channels for sharing intelligence and data, which are insufficient to address the sophisticated and rapidly evolving nature of financial crime and delinquent behavior.

Innovation Solution

A blockchain-based system for collaborative analytics is implemented, where financial institutions store and analyze data analytics and derive metrics, allowing for the sharing of fraud detection insights without revealing proprietary models, thereby enhancing the ability to identify fraudulent activity more quickly and improve depositor confidence.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If traditional channels are used for sharing fraud intelligence, then data privacy and security are maintained, but the speed and adaptability of fraud detection are insufficient

Engineering Contradiction:

Improvefraud detection speedVSAvoidproprietary model exposure

Core Design Contradiction:

SpeedVSLoss of information

Solution Approach 1:

The system segments fraud detection capabilities into two distinct layers: proprietary analytical models that remain locally housed at each institution, and processed fraud indicators that are shared on the blockchain. This segmentation allows institutions to share fraud intelligence without exposing their proprietary models, resolving the contradiction between detection speed and information loss.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The blockchain acts as an intermediary layer that receives processed fraud indicators from participating institutions, stores them immutably, and makes them accessible to all participants. This intermediary mechanism enables rapid sharing of fraud intelligence while maintaining the security and privacy of underlying proprietary models.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Adaptability or versatility

If institutions share comprehensive fraud data, then collective fraud detection capability improves, but proprietary information and analytical models are exposed

Engineering Contradiction:

Improvefraud detection adaptabilityVSAvoidproprietary model exposure

Core Design Contradiction:

Adaptability or versatilityVSLoss of information

Solution Approach 1:

The system extracts only the necessary fraud detection indicators from proprietary models and places them on the blockchain, while leaving the complete analytical models at their original institutions. This extraction approach enables institutions to benefit from collective fraud detection adaptability without exposing their proprietary information.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

By segmenting the fraud detection system into local proprietary models and shared fraud indicators, institutions can collaborate to improve fraud detection adaptability while maintaining control over their sensitive proprietary assets.

Inventive Principle:

Principle #1Segmentation

3Productivity

If real-time fraud intelligence sharing is implemented, then fraud detection responsiveness improves, but system complexity increases

Engineering Contradiction:

Improvefraud detection productivityVSAvoidsystem architecture complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The blockchain platform provides universal functionality for storing, verifying, and distributing fraud indicators across all participating institutions. This multi-functional platform reduces the need for individual institutions to build complex peer-to-peer sharing systems, thereby improving fraud detection productivity while managing system complexity.

Inventive Principle:

Principle #6Universality (Multi-functionality)

4Measurement precision

If decentralized data sharing is implemented, then fraud detection accuracy improves, but data security and verification complexity increase

Engineering Contradiction:

Improvefraud detection precisionVSAvoidverification system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The blockchain serves as a trusted intermediary that provides decentralized verification of fraud indicators through its immutable ledger and consensus mechanisms. This intermediary approach enables institutions to achieve improved fraud detection precision through access to multiple data sources while the blockchain manages the complexity of verification automatically.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS11227287B2Collaborative analytics for fraud detection through a shared public ledger

Publication Date: 2022.01.18 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

An example operation may include one or more of a computer deriving a first set of metrics from processing a first and second set of data analytics, the sets associated with a subject matter. The operation further comprises the one or more computer deriving a second set of metrics from processing a third and fourth sets of data analytics, the third and fourth sets associated with the subject matter. The operation further comprises the one or more computer publishing the first and second set of metrics. The operation further comprises the one or more computer receiving a first plurality of requests for processing of analytics using the first set of metrics. The operation further comprises the one or more computer receiving a second plurality of requests for processing of analytics using the second set of metrics. The operation further comprises the one or more computer maintaining tallies of the requests.