Transaction Risk Identification via Network Sub-Partitioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic commerce systems are ineffective in identifying transaction risks due to easily discoverable rules, allowing malicious users to sidestep security measures and evade risk identification.
Innovation Solution
A method and apparatus that build entities and activities related to transactions into a relationship network, partitioning it into sub-networks based on connectivity, and using risk identification information including static and dynamic properties to identify potential risks, making it difficult for users to evade detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If simple transaction amount rules are used for risk identification, then the system is easy to operate and implement, but malicious users can easily discover and sidestep the rules
Solution Approach 1:
The patent segments the relationship network into multiple sub-networks based on connectivity, where each sub-network represents a cluster of related entities. This segmentation allows the system to analyze transaction risks within localized contexts rather than relying on simple global rules, making it harder for malicious users to evade detection while maintaining operational feasibility.
Solution Approach 2:
The patent transitions from analyzing single transaction attributes (one-dimensional) to analyzing multi-dimensional network properties including connectivity patterns, entity relationships, and sub-network characteristics. This dimensional expansion creates a more robust risk identification framework that cannot be easily circumvented by manipulating single transaction parameters.
2Reliability
If complex network analysis is used for risk identification, then the reliability of risk detection improves, but the device complexity increases
Solution Approach 1:
By dividing the large relationship network into smaller sub-networks based on connectivity thresholds, the system reduces computational complexity while preserving detection effectiveness. Each sub-network can be analyzed independently, making the overall system more manageable despite the sophisticated analysis performed.
Solution Approach 2:
The patent extracts only the essential risk identification information from the relationship network, such as connectivity patterns and sub-network properties, rather than processing all possible network attributes. This extraction approach maintains high detection reliability while reducing system complexity.
3Ease of manufacture
If static rules are used for risk identification, then the system is simple to maintain, but the adaptability to new fraud patterns decreases
Solution Approach 1:
The patent implements dynamic risk identification by continuously analyzing network connectivity changes and entity relationship evolutions. The system adapts to new fraud patterns by detecting changes in network structure and behavior, rather than relying on fixed static rules that require frequent manual updates.
Solution Approach 2:
The system incorporates feedback mechanisms where risk identification results and network analysis data are used to continuously refine and update the relationship network model. This feedback loop enables the system to automatically adapt to emerging fraud patterns while maintaining relatively simple maintenance procedures.
Data Source
AI summary
A method and an apparatus for identifying a transaction risk are disclosed. The method includes obtaining risk identification information of a sub-network to which a node relating to a transaction to be identified belongs; and identifying a risk of the transaction to be identified based on the risk identification information of the sub-network to which the node relating to the transaction to be identified belongs, wherein the sub-network is a network acquired by partitioning a relationship network based on connectivity, the relationship network is a network built up with entities and activities relating to a plurality of transactions. Embodiments of the present disclosure build up entities and activities relating to a transaction to be identified into a relationship network, and identify whether a risk exists in the transaction to be identified using risk identification information of the network which is difficult to be found or changed, and thus are able to identify a transaction risk in a more effective manner.