Authorization Optimizer Timing for NSF Recurring Payment Retries
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Recurring payment transactions often fail due to non-sufficient funds (NSF) errors, leading to increased decline rates and network traffic, which erodes fraud model performance and analytics.
Innovation Solution
A computer-implemented method using an authorization optimizer model, such as a gradient boosting model or LSTM, to determine an optimal time slot for retrying recurring payment transactions based on historical transaction data, including features like transaction velocity and spending patterns, to improve authorization accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If merchants re-try recurring payment transactions immediately after NSF decline, then payment processing speed is improved, but network traffic increases and fraud model performance deteriorates
Solution Approach 1:
The system performs preliminary analysis of historical transaction data and user spending patterns before authorizing a retry transaction. The authorization optimizer model predicts the likelihood of successful authorization in advance, preventing unnecessary retry transactions that would generate harmful network traffic and degrade fraud model performance.
Solution Approach 2:
The system incorporates feedback from historical transaction outcomes and spending pattern analysis to dynamically adjust retry authorization decisions. By continuously learning from past NSF declines and successful payments, the model optimizes retry timing to balance processing speed with network load management.
2Measurement precision
If authorization optimizer model uses complex historical transaction data analysis, then authorization accuracy is improved, but system complexity increases
Solution Approach 1:
The system extracts only the most relevant features from historical transaction data, such as spending patterns, transaction velocity, and user behavior metrics. By selecting and focusing on key predictive features rather than processing all available data, the model achieves high authorization accuracy while maintaining manageable system complexity.
Solution Approach 2:
The system transforms complex historical transaction data into simplified predictive parameters that capture essential user behavior patterns. By changing the representation of transaction data into optimized features suitable for the authorization optimizer model, the system achieves accurate predictions without proportionally increasing computational complexity.
Data Source
AI summary
Methods and server systems for improving accuracy of authorization optimizer are described herein. Method performed by server system includes receiving a Non-Sufficient Funds (NSF) error message from an acquirer server. Method includes accessing historical transaction data from a transaction database. The historical transaction data includes transaction related information associated with a plurality of users. Method includes generating a plurality of transaction features associated with the user based on the historical transaction data. Method includes determining via an authorization optimizer model, an optimal time slot from a plurality of time slots for the user based on the plurality of transaction features associated with the user. The optimal time slot indicates an optimal time window for the acquirer server to transmit an upcoming recurring payment request to the payment account of the user. Method includes facilitating transmission of a notification message including the optimal time slot to the acquirer server.