Online transaction-oriented fraud detection method based on individual behavior modeling
A technology for online transactions and detection methods, applied in payment systems, semantic tool creation, unstructured text data retrieval, etc., can solve problems such as poor rule adaptability and inability to detect novel fraudulent behaviors
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0050] A system structure diagram of an individual behavior modeling method for real-time detection of online transaction fraud, such as figure 2 shown. The whole program is divided into two parts:
[0051] In the first part, the heterogeneous information network is generated by using the relationship graph and the vector representation that can mine the connection between transaction attributes is obtained by learning the representation of the heterogeneous network;
[0052] The second part is the process of establishing an individual behavior model and predicting the possibility of abnormal transactions in the case of learning the vector representation of the node.
[0053] In the first part, the relationship map generates heterogeneous information network and heterogeneous network representation learning, the process is as follows:
[0054] enter:
[0055] The raw data field of the user network payment transaction,
[0056] Adjust the weight hyperparameters α, β,
[0...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com