Network Benchmark Recommendations for Rapid Transaction Assessment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing processing networks face challenges in efficiently assessing and addressing improper transactions, such as fraudulent activities, due to the substantial volume of interactions, which impedes comprehensive assessment and requires time-consuming investigations.
Innovation Solution
A system and method that utilizes subject matter expertise and trigger rules based on objective metrics to identify timely and actionable recommendations for participants, reducing the assessment of substantial network data and providing targeted recommendations to address specific network issues.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If comprehensive assessment of network data is performed to identify improper transactions, then detection accuracy is improved, but assessment time increases significantly
Solution Approach 1:
The patent extracts and analyzes only the most critical metrics (authorization rate, fraud rate, net fraud rate) from the substantial volume of network data, rather than performing comprehensive assessment of all data. This extraction approach enables timely identification of improper transactions while maintaining detection accuracy through focused analysis of key performance indicators.
Solution Approach 2:
The patent transforms the assessment approach by changing from analyzing raw transaction data to analyzing aggregated metrics and rates. By parameterizing the data into standardized metrics (authorization rate, fraud rate, net fraud rate) and comparing them against benchmarks, the system achieves both speed and accuracy in detecting improper transactions without time-consuming comprehensive assessments.
2Measurement precision
If comprehensive assessment of participants is conducted to address network issues, then problem identification is improved, but time required for investigation increases
Solution Approach 1:
The patent extracts and focuses on specific critical metrics (authorization rate, fraud rate, net fraud rate) rather than conducting comprehensive assessment of all participant data. This targeted extraction enables precise problem identification in the area of improper transactions while significantly reducing the time required for investigation.
Solution Approach 2:
The patent establishes benchmarks and trigger rules in advance that define when and how to investigate specific issues. By pre-setting the criteria for problematic transactions (e.g., authorization rate below threshold, fraud rate above threshold), the system enables rapid problem identification without time-consuming preliminary investigations, as the benchmarks provide immediate guidance for action.
3Reliability
If substantial network data is assessed to identify fraudulent transactions, then fraud detection capability is improved, but processing speed decreases
Solution Approach 1:
The patent extracts and processes only the essential metrics (authorization rate, fraud rate, net fraud rate) from the substantial network data, rather than analyzing all transaction details. This extraction enables maintained fraud detection capability through focused analysis of key indicators while significantly improving processing speed by reducing the volume of data that requires evaluation.
Solution Approach 2:
The patent transforms the data processing approach by converting raw transaction data into aggregated rate metrics. By parameterizing the data into standardized rates (authorization rate, fraud rate, net fraud rate) and comparing these against pre-established benchmarks, the system maintains reliable fraud detection while achieving faster processing speeds due to the simplified metric-based comparison.
Data Source
AI summary
Systems and methods are provided for identifying recommendations, based on network benchmarks. One example method includes accessing, by a service platform computing device, data specific to a participant, the data representative of multiple transactions; calculating a first metric based on the accessed data, the first metric indicative of a rate of the transaction represented by the accessed data; identifying a recommendation based on a trigger rule, which defines a relationship between at least one benchmark and the first metric; and displaying the recommendation to a user associated with the participant.