Community Database for Cryptic Transaction Description Translation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Customer service call centers face a high volume of inquiries regarding unclear bank account transaction descriptions due to the lack of standardization in transaction descriptions within NACHA and credit card processing rules, making it complex and costly to translate these descriptions into customer-recognizable terms.

Innovation Solution

A community-driven database that allows users to provide and share recognizable descriptions, categories, and location information for cryptic transaction descriptions, enabling customers to search and update transaction sources, merchants, and locations, thereby improving understanding and clarity.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If transaction descriptions use free-form text fields with abbreviations and codes meaningful to merchants, then merchants can use any description they deem acceptable, but customer service call centers receive a large number of calls related to unrecognized account transaction descriptions

Engineering Contradiction:

Improvemerchant description flexibilityVSAvoidcustomer understanding

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The patent introduces a translation layer that acts as an intermediary between merchant descriptions and customer understanding. This translation layer uses machine learning models trained on transaction data to automatically translate cryptic merchant descriptions into recognizable customer-friendly terms, thereby maintaining merchant flexibility while improving customer comprehension without requiring changes to either merchant or customer systems

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system enables self-service by allowing customers to interact with transaction descriptions through intuitive interfaces that automatically interpret and explain charges. Customers can review translated descriptions, report issues, and receive explanations without needing to contact customer service, thereby reducing call volume while maintaining ease of use

Inventive Principle:

Principle #25Self-service

2Adaptability or versatility

If there are no transaction description standardization requirements within NACHA and Credit Card Association processing rules, then ACH processors and merchants are free to choose any description, but a systematic attempt to translate unrecognizable descriptions would be very complex, problematic and costly to operate

Engineering Contradiction:

Improvedescription freedomVSAvoidtranslation system complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent transforms the translation problem from a complex rule-based system into a learnable parameter optimization problem. By training machine learning models on historical transaction data with labeled customer-understandable descriptions, the system automatically learns the mapping parameters between merchant codes and customer-friendly terms, thereby simplifying the translation mechanism while maintaining adaptability across diverse merchants

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent replaces the mechanical rule-based translation approach with an intelligent system based on machine learning and natural language processing. Instead of manually configuring translation rules for each merchant, the system uses algorithms to automatically learn and adapt translation patterns from data, significantly reducing system complexity and operational costs

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If transaction descriptions pass through multiple networks and processing systems, then descriptions can be transmitted flexibly, but systematic translation attempts become very complex and costly

Engineering Contradiction:

Improvenetwork transmission flexibilityVSAvoidtranslation efficiency

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent implements preliminary action by pre-training translation models on extensive transaction data before deployment. The machine learning models are trained in advance to recognize patterns across multiple networks and processing systems, enabling them to accurately translate descriptions without requiring real-time complex processing, thereby maintaining network flexibility while improving translation efficiency

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11501293B1Systems and methods for presenting recognizable bank account transaction descriptions compiled through customer collaboration

Publication Date: 2022.11.15 UNITED SERVICES AUTOMOBILE ASSOCIATION (USAA)

AI summary

A system and methods for leveraging a community of users to collaboratively identify bank or investment account transaction descriptions by providing common, more recognizable description, category and location information used most often by the community. A database may be maintained that is accessible by the customer/user community to view, update and provide understandable descriptions for such cryptic descriptions. The database may be searchable such that a customer/user may search a description to determine or update the source of the transaction.