Identity-Map Clustering for Abnormal E-Commerce Transactions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing number of abnormal transactions, such as fraud and illegal product sales, in e-commerce platforms like DangGeun Market and JoongGo-Nara, necessitates a technology to identify and prevent such activities.
Innovation Solution
A method and system that generate and analyze an identity graph based on transaction and user information to detect abnormal users by combining various identifiers, including device IDs, payment information, and other modifiable data to create a comprehensive identifier, and use this to track and prevent abnormal transactions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional transaction monitoring methods are used, then the system is simple to operate, but it cannot effectively identify abnormal transactions such as fraud and illegal product sales
Solution Approach 1:
The system segments the complex detection task into distinct functional modules: a map generation module that creates identity maps from historical data, a transaction information collection module that gathers new transaction data, and a transaction information analysis module that performs the actual abnormality detection. This segmentation allows each module to specialize in specific aspects of the detection process, improving overall reliability while making the system more manageable and maintainable despite its complexity
Solution Approach 2:
The system performs preliminary actions by pre-generating identity maps from historical transaction information before actual detection occurs. The map generation module creates comprehensive identity maps that link various identifiers (device IDs, payment information, user profiles) to user identities in advance. When new transactions need to be analyzed, the system can quickly query these pre-built maps rather than processing raw data in real-time, significantly improving detection accuracy and speed
2Measurement precision
If multiple identifiers are combined to create comprehensive user profiles, then abnormal user detection accuracy improves, but data processing complexity increases
Solution Approach 1:
The system merges multiple identifiers including device IDs, payment information, user profiles, and transaction histories into unified identity maps. The transaction information analysis module combines these diverse data elements to create comprehensive user profiles that enable accurate identification of abnormal users. By merging related identifiers and their associated data, the system achieves high measurement precision in detecting fraudulent activities while managing data processing complexity through structured integration
Solution Approach 2:
The identity map serves as an intermediary structure that connects various identifiers (device IDs, payment information, user profiles) to user identities. Rather than directly processing and correlating all raw identifier data, the system uses the pre-generated identity map as a mediator to link identifiers to users. This intermediary approach simplifies the processing complexity by providing a structured lookup mechanism while maintaining high identification accuracy through comprehensive data associations
3Speed
If real-time transaction analysis is performed, then abnormal transactions are detected quickly, but processing time and computational resources increase
Solution Approach 1:
The system performs preliminary processing by pre-generating identity maps from historical transaction data before real-time detection is needed. The map generation module creates and stores these comprehensive identity maps in advance, organizing user identifiers, device IDs, payment information, and transaction histories into query-optimized structures. During real-time operation, the transaction information analysis module can quickly query these pre-built maps without performing complex data aggregation, achieving fast detection speeds while reducing real-time computational resource consumption
Solution Approach 2:
The system segments the detection process into offline map generation and online real-time analysis phases. The computationally intensive tasks of data aggregation, identifier correlation, and identity map construction are performed offline by the map generation module using historical data. The online phase handled by the transaction information analysis module only requires querying pre-generated maps and comparing new transactions against established patterns, dramatically reducing real-time computational resource consumption while maintaining high detection speed
Data Source
AI summary
The present invention relates to a method and system for tracking abnormal transactions in e-commerce, and an object of the present invention is to track abnormal transactions by analyzing complex characteristic data of product information uploaded to an e-commerce platform. In order to achieve this object, a method for detecting an abnormal transaction in an electronic device according to the present invention includes: step a of generating an identity map based on first transaction information previously stored in an e-commerce server; step b of collecting second transaction information newly uploaded to the e-commerce server; step c of extracting a first identifier and second identifiers included in the second transaction information and generating a third identifier by combining the plurality of second identifiers; and step d of determining whether the second transaction information is an abnormal transaction by searching the identity map for the first identifier and the third identifier.