Cognitive Transaction Platform for Automated Channel Selection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current payment processing systems face inefficiencies due to manual interventions required when transfer channels experience backlogs, leading to delayed or failed fund transfers, which negatively impact payer satisfaction.

Innovation Solution

A transaction processing system utilizing a transaction control platform with machine learning algorithms to determine and switch between available transfer channels based on real-time attributes such as queue lengths, wait times, and usage costs, ensuring timely and successful fund transfers.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If manual intervention is used to select a new transfer channel when a backlog occurs, then the transfer channel can be changed to resolve the backlog, but the process becomes inefficient and laborious due to the large number of factors that need to be accounted for

Engineering Contradiction:

Improveautomated transfer channel selectionVSAvoidcomplexity of evaluating multiple transfer channel factors

Core Design Contradiction:

Extent of automationVSDevice complexity

Solution Approach 1:

The system enables automated self-service by implementing machine learning models that autonomously evaluate multiple transfer channel factors (queue lengths, wait times, success rates, costs) and select optimal channels without human intervention. The cognitive learning system continuously learns from historical data and automatically adapts to changing conditions, resolving the backlog issue while eliminating manual labor.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system dynamically changes evaluation parameters by considering multiple factors including queue lengths, average wait times, success rates, and usage costs of different transfer channels. The machine learning model adjusts the weight and importance of these parameters based on learned patterns, enabling efficient automated decision-making that accounts for the complex multitude of factors without manual intervention.

Inventive Principle:

Principle #35Parameter changes

2Reliability

If multiple factors are evaluated to select an optimal transfer channel, then the quality of selection improves, but the processing time and computational resources increase

Engineering Contradiction:

Improveaccuracy of transfer channel selectionVSAvoidtime for evaluating transfer channel factors

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-processing and storing historical transfer data, pre-evaluating transfer channel attributes, and pre-training machine learning models before actual fund transfers occur. This allows the system to quickly retrieve pre-computed information and make rapid decisions during real-time transfers, reducing the time required to evaluate multiple factors while maintaining high selection accuracy.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system replaces manual mechanical evaluation processes with automated machine learning algorithms that can process multiple factors simultaneously. The cognitive learning system uses computational models to evaluate queue lengths, wait times, success rates, and costs in parallel, significantly reducing the time required compared to sequential manual analysis while improving selection reliability through consistent algorithmic application.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If real-time monitoring of transfer channel attributes is implemented, then the system can dynamically switch channels to avoid backlogs, but the system complexity and data processing requirements increase

Engineering Contradiction:

Improvespeed of fund transfer processingVSAvoidcomplexity of real-time monitoring system

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The machine learning system serves multiple functions simultaneously: it monitors transfer channel attributes in real-time, evaluates multiple factors, predicts backlog conditions, selects optimal channels, and learns from outcomes. This multi-functional cognitive system consolidates what would otherwise require separate monitoring, analysis, decision-making, and learning components, reducing overall system complexity while maintaining high productivity through integrated automated operations.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS12169816B2Automated transaction processing based on cognitive learning

Publication Date: 2024.12.17 BANK OF AMERICA CORP

AI summary

Aspects of the disclosure relate to systems for processing transactions between two entities. A transaction control platform may determine attributes associated with different transfer channels between the two entities. Based on the determined attributes, the transaction control platform may determine a transfer channel to be used for transmitting a message corresponding to the transaction. The transaction control platform may use machine learning algorithms to identify an optimal transfer channel that meets particular desired factors.