Payment Routing System Using Scaled Scores
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing payment systems often result in suboptimal payment processing and higher costs due to predetermined merchant settings, leading to failed transactions and inefficient routing methods.
Innovation Solution
A system that uses processors and transceivers to receive payment transaction messages, generate scaled scores based on historical data, and apply contribution rules to optimize payment routing according to the likelihood of settlement, allowing for real-time adjustments and feedback-driven algorithm retraining.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If predetermined merchant settings are used for payment routing, then the system is simple to operate, but payment processing efficiency deteriorates and transaction failures increase
Solution Approach 1:
The system automatically routes payments by analyzing account data, transaction characteristics, and settlement likelihood without requiring merchant configuration. The payment system self-optimizes routing decisions based on real-time data, eliminating the need for manual merchant settings while improving processing efficiency
Solution Approach 2:
The system continuously monitors payment outcomes, account balances, and settlement success rates, using this feedback to dynamically adjust routing decisions. This closed-loop approach allows the system to learn from past transactions and improve routing efficiency over time without merchant intervention
2Device complexity
If predetermined merchant settings are used for payment routing, then device complexity is reduced, but transaction costs increase
Solution Approach 1:
The payment system automatically selects cost-effective routing options by analyzing multiple accounts and settlement probabilities, eliminating the need for complex merchant-configured routing rules while reducing transaction costs through intelligent, data-driven decision-making
Solution Approach 2:
The system dynamically changes routing parameters based on real-time account data, transaction amounts, and settlement likelihood calculations. By adjusting routing decisions based on these varying parameters, the system minimizes costs without requiring fixed, pre-configured settings
3Measurement precision
If scaled score algorithm with multiple components is implemented, then payment routing accuracy is improved, but device complexity increases
Solution Approach 1:
The scaled score algorithm is divided into multiple independent components, each evaluating specific aspects of settlement likelihood (e.g., account balance, transaction history, account characteristics). This segmentation allows the complex prediction task to be broken into manageable, modular components that can be processed efficiently
Solution Approach 2:
The multi-component scaled score algorithm serves multiple functions: it evaluates settlement likelihood, ranks accounts by probability of success, and provides explanatory metadata about contributing factors. This universal approach handles various payment scenarios with a single integrated system
4Reliability
If multiple accounts are evaluated for payment routing, then settlement likelihood is improved, but processing time increases
Solution Approach 1:
The system pre-calculates and stores account characteristics, historical performance data, and baseline settlement probabilities for multiple accounts. This preliminary preparation allows rapid evaluation during actual payment routing without requiring time-consuming real-time analysis of each account
Data Source
AI summary
A system for payment routing programmed to: receive a payment transaction message relating to a putative transaction, the payment transaction message containing putative transaction data identifying an account of an accountholder and a transaction amount corresponding to the putative transaction; input at least some of the putative transaction data to a scaled score algorithm to generate a scaled score representing the likelihood of settlement of the putative payment transaction on a date, the scaled score algorithm including a plurality of components each respectively outputting a value and the scaled score being based on the plurality of values; generate metadata regarding the scaled score by applying a plurality of contribution rules to the values, the metadata comprising significance indicators for the components with respect to the generation of the scaled score; and output the scaled score and the metadata regarding the scaled score in response to the payment transaction message.


