Transaction Attribute Processing for Fast Risk Reason Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing transaction systems delay or deny transactions without providing clear reasons, requiring time-consuming and resource-intensive querying of complex risk evaluation models, and customer support teams lack the expertise to explain these decisions effectively.
Innovation Solution
A computing system processes user queries by comparing transaction attributes with training data to identify relevant attributes, modifying them to simulate transactions, and evaluating risk levels, allowing customer support to quickly identify factors contributing to transaction denials or delays without revealing sensitive information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a risk evaluation model uses hundreds or thousands of variables to determine transaction risk, then the accuracy of risk assessment is improved, but the time and computational resources required to identify specific reasons for transaction denial increase significantly
Solution Approach 1:
The patent segments the large set of risk variables into hierarchical groups and categories. Instead of analyzing all hundreds or thousands of variables simultaneously, the system divides them into manageable segments that can be processed separately, reducing the time required to identify specific denial reasons while maintaining assessment accuracy.
Solution Approach 2:
The patent extracts and identifies the specific subset of variables that actually contributed to a transaction denial from the full set of risk variables. By taking out only the relevant variables that caused the denial, the system provides actionable insights without requiring analysis of all variables, thus reducing time and computational resources.
2Measurement precision
If a merchant's customer support team queries the risk determination model to understand transaction denials, then the technical expertise required is improved, but the complexity of the support team's operations increases
Solution Approach 1:
The patent introduces an intermediary system that translates complex risk model outputs into understandable explanations for customer support teams. This intermediary layer processes the technical risk assessment data and presents it in a simplified format, allowing support staff to understand transaction denials without needing deep technical expertise in the risk evaluation model.
Solution Approach 2:
The patent creates simplified copies or representations of the complex risk variables and their relationships. Instead of requiring support teams to interact with the full complexity of the risk model, the system generates simplified copies of the relevant information that capture the essential reasons for denial in an easily interpretable format.
3Measurement precision
If the system processes all transaction attributes to determine risk factors, then the completeness of risk analysis is improved, but the data processing efficiency decreases
Solution Approach 1:
The patent applies partial action by processing only the necessary subset of transaction attributes required to determine risk factors, rather than analyzing all attributes. The system identifies and processes only those attributes that have a meaningful impact on risk assessment, achieving sufficient completeness without the computational overhead of processing every single attribute.
Solution Approach 2:
The patent changes parameters by dynamically adjusting which transaction attributes are processed based on the specific transaction context and risk indicators. Instead of always processing all attributes, the system adapts the processing scope by changing parameters such as attribute selection criteria and processing depth, thereby maintaining analysis completeness while improving processing efficiency.
Data Source
AI summary
Systems and methods for processing machine learning attributes are disclosed. An example method includes: identifying a user transaction associated with a set of transaction attributes and a first transaction status; selecting, based on a risk evaluation model, a first plurality of transaction attributes from the set of transaction attributes; modifying a first value of a first transaction attribute in the first plurality of transaction attributes to produce a first modified plurality of transaction attributes; determining, based on the risk evaluation model, that the first modified plurality of transaction attributes identify a second transaction status different from the first transaction status; and in response to the determining, identifying the first transaction attribute as a risk attribute associated with the user transaction.