ML-Guided Transaction Anomaly Resolution via Targeted Mobile Queries

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems for resolving suspicious account activity, such as unauthorized transactions, often require significant user delay and resource-intensive customer service interactions, leading to prolonged resolution times and potential further unauthorized transactions.

Innovation Solution

A mobile application leveraging biometric login and a machine learning model to present targeted questions to users for immediate resolution of suspicious activity, reducing the need for customer service representative intervention.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a user calls customer service to resolve suspicious activity, then the issue can be addressed with human assistance, but the resolution time is significantly delayed and resource consumption increases

Engineering Contradiction:

Improveresolution accuracyVSAvoidresolution time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system enables users to resolve suspicious transactions independently through automated messaging interfaces. Users receive notifications about suspicious activity and can respond through pre-defined options or custom messages, allowing the system to autonomously resolve issues without requiring customer service representative intervention.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical system of human customer service representatives with an automated computer-based messaging system. The system uses algorithms to analyze user responses, determine transaction legitimacy, and execute resolutions automatically, substituting human mechanical processes with automated computational processes.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If traditional alert-based systems are used to notify users of suspicious activity, then users are informed of the issue, but the system does not provide the ability for immediate resolution

Engineering Contradiction:

Improveuser notificationVSAvoidresolution efficiency

Core Design Contradiction:

Ease of operationVSProductivity

Solution Approach 1:

The system merges the notification function with the resolution function into a single integrated messaging interface. Instead of separate alert and resolution processes, users receive notifications and can resolve issues through the same communication channel, combining multiple functions into one streamlined interaction.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The system prepares resolution options and response templates in advance, allowing users to quickly address suspicious transactions without needing to compose detailed explanations. Pre-defined response options are provided based on the type of suspicious activity detected, enabling immediate action.

Inventive Principle:

Principle #10Preliminary action

3Difficulty of detecting and measuring

If customers service representatives are deployed to handle suspicious activity calls, then comprehensive investigation can be conducted, but resource consumption and operational costs increase

Engineering Contradiction:

Improveinvestigation capabilityVSAvoidresource consumption

Core Design Contradiction:

Difficulty of detecting and measuringVSLoss of energy

Solution Approach 1:

The system extracts the investigation and resolution functions from human customer service representatives and implements them through automated algorithms. The computer system independently analyzes transaction data, evaluates user responses, and determines resolution actions without requiring human representative involvement for routine cases.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system creates automated copies of customer service representative capabilities through algorithms that can analyze transactions, evaluate risk, and make resolution decisions. These digital copies perform the investigative function at scale without consuming human resources.

Inventive Principle:

Principle #26Copying

Data Source

PatentUS20260080414A1Machine learning model for self-service transaction anomaly resolution

Publication Date: 2026.03.19 WELLS FARGO BANK NA

AI summary

A method may include determining suspicious activity with respect to a user account, the suspicious activity including at least one transaction on the user account; transmitting a notification to a computing device associated with the user account, the notification identifying the suspicious activity and including a link into an application installed on the computing device to confirm the suspicious activity; receiving, from the application, an indication that the notification was activated on the computing device; and in response to the indication: selecting a subset of queries of a plurality of queries to present on a display device of the computing device via the application; receiving answers to the subset of queries via the application; processing the answers to generate a resolved status of the suspicious activity.