Transaction Risk Stratification via Dynamic MID Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In traditional card-not-present transactions, merchants face high false positive rejection rates due to limited data available to credit card issuers for risk analysis, leading to lost sales opportunities and increased chargeback costs for both merchants and issuers.
Innovation Solution
A system that assigns transactions to different merchant identification numbers (MIDs) based on risk scores and target chargeback rates, using a computer device to evaluate transaction information, determine risk scores, and dynamically allocate transactions to stratums to optimize approval rates and reduce chargebacks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the retail bank performs conservative risk analysis and rejects transactions with potential fraud or chargeback risk, then the chargeback rate is reduced, but the false positive rate increases and transaction approval rate decreases
Solution Approach 1:
The patent segments transactions into different risk categories (low-risk, medium-risk, high-risk) based on risk score thresholds. This segmentation allows the system to apply different approval strategies to different transaction types, thereby reducing false positives while maintaining chargeback control. Low-risk transactions are automatically approved, medium-risk transactions undergo additional verification, and high-risk transactions are rejected, resolving the contradiction between approval rate and chargeback rate.
Solution Approach 2:
The system dynamically adjusts risk score thresholds and evaluation parameters based on historical chargeback data and transaction patterns. By changing the parameter values (thresholds) rather than the system structure, the bank can optimize the balance between approval rate and chargeback rate. The thresholds are adjusted to reflect current risk levels, allowing flexible control over the trade-off between false positives and actual fraud prevention.
2Device complexity
If the retail bank uses limited pre-defined transaction fields for risk analysis, then the data processing complexity is reduced, but the measurement precision of risk assessment decreases
Solution Approach 1:
The system performs preliminary actions by pre-defining risk score thresholds and transaction field mappings before actual risk assessment occurs. This preliminary structuring of data fields and risk criteria allows the system to process transactions efficiently using standardized formats, while still achieving accurate risk assessment through the pre-configured evaluation framework. The complexity is managed upfront rather than during real-time processing.
Solution Approach 2:
The patent introduces an intermediary risk scoring mechanism that bridges the gap between limited transaction fields and comprehensive risk assessment. The risk score acts as an intermediary variable that aggregates information from multiple pre-defined fields and transforms them into a single actionable metric. This intermediary layer enables accurate risk measurement without requiring complex processing of all individual fields.
3Reliability
If the merchant implements screening to predict chargeback risk, then the chargeback prevention effectiveness is improved, but the transaction processing time and operational complexity increase
Solution Approach 1:
The system applies partial screening actions based on risk levels rather than performing comprehensive screening on all transactions. Low-risk transactions receive minimal or no additional screening, while only medium and high-risk transactions undergo more extensive evaluation. This partial action approach maintains chargeback prevention effectiveness for risky transactions while minimizing processing time delays for the majority of low-risk transactions.
Solution Approach 2:
The patent implements feedback mechanisms where chargeback outcomes and risk predictions are continuously monitored and used to adjust future risk assessment parameters. This feedback loop improves chargeback prevention effectiveness over time without requiring increased processing time for each individual transaction, as the system learns from historical data to make faster, more accurate predictions.
Data Source
AI summary
Examples described herein generally relate to a computer device including a memory, and at least one processor configured to process a transaction. The computer device receives customer transaction information. The computer device evaluates the customer transaction information to determine a risk score for the transaction. The computer device assigns the transaction, based on the risk score, to one of a plurality of stratums including at least a first stratum and a second stratum. The computer device selects a merchant identifier (MID) from at least a first MID associated with the first stratum and a second MID associated with the second stratum based on at least the assigned stratum and a target chargeback rate for at least one of the first MID or the second MID. The computer device transmits the transaction information and the selected MID to an issuing bank.