Anomalous Attribute Classification for Electronic Activity Verification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
There is a technological challenge in detecting and correcting user-specified data errors in electronic activities without an authoritative source of truth, as these errors can be due to malicious behavior or user mistakes, and existing systems lack efficient methods to determine the correct data or values.
Innovation Solution
A computer-based system that receives electronic activity verifications, generates a feature vector from verified and user-specified values, uses an anomalous attribute classification model to classify anomalies, and displays a dispute GUI to allow users to dispute incorrect activities, canceling the activity and training the model based on user interactions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If user-specified values are accepted without verification, then ease of operation is improved, but reliability deteriorates due to potential errors and fraud
Solution Approach 1:
The system performs preliminary verification of user-specified values against verified values before accepting the electronic activity. The verification system proactively checks data accuracy, generates anomaly classifications, and prevents erroneous activities from being processed, thereby ensuring reliability while maintaining ease of operation through automated validation.
2Reliability
If automated verification systems are implemented, then reliability is improved, but device complexity increases
Solution Approach 1:
The verification system operates autonomously by automatically comparing user-specified values against verified values, generating anomaly classifications, and executing dispute processes without requiring complex external validation infrastructure. The system self-manages the verification workflow, reducing overall device complexity while maintaining high reliability.
3Measurement precision
If anomaly detection is performed on all electronic activities, then measurement precision is improved, but productivity deteriorates due to increased processing time
Solution Approach 1:
The system applies anomaly detection selectively rather than uniformly to all electronic activities. The verification system focuses processing on activities with higher risk profiles or those that deviate from expected patterns, achieving high measurement precision for critical cases while maintaining overall productivity by avoiding unnecessary verification of low-risk transactions.
Data Source
AI summary
Systems and methods of the present disclosure enable a processor to automatically detect anomalous user-specified data by receiving an electronic activity verification associated with an electronic activity of a user account, including a value associated with an electronic activity, and a user-specified value indicative of an additional value specified by a user for the electronic activity. The processor generates a feature vector including the verified value and the user-specified value and utilizes an anomalous attribute classification model to ingest the feature vector to determine an anomaly classification based on learned model parameters. The processor generates a dispute graphical user interface (GUI) including an alert message and a dispute interface element, that upon a user interaction causes an electronic request to dispute the electronic activity verification to prevent an execution of the electronic activity. The processor cancels the electronic activity to prevent the execution of the electronic activity.