Detecting Selective Omissions in Open Banking Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems in open banking environments face inefficiencies and errors in detecting selective omissions in customer-provided payment transaction data, which can manipulate creditworthiness assessments.
Innovation Solution
An AI-driven system monitors and maps customer financial transactions to identify anomalies by associating detected events with sets of words, determining multinomial distributions over archetypes, and generating scores to indicate potential omissions, thereby providing a probabilistic assessment of missing information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If customers selectively share only positive transaction data in open banking environments, then creditworthiness assessment accuracy deteriorates, but data sharing compliance improves
Solution Approach 1:
The system performs preliminary analysis of shared transaction data against predicted archetypes before final creditworthiness determination. By comparing actual shared data with expected data patterns in advance, the system can detect selective omissions and adjust assessments accordingly, ensuring reliable credit evaluation even when customers share incomplete data sets
Solution Approach 2:
The system implements feedback mechanisms where detection results from collaborative counterfactual interventions are fed back into the credit assessment process. When selective omission is detected, the system adjusts the creditworthiness evaluation by incorporating predicted archetype information, creating a closed-loop system that continuously improves assessment accuracy despite incomplete data sharing
2Speed
If traditional fraud detection methods are used, then detection speed is slow, but system complexity remains low
Solution Approach 1:
The patent replaces traditional mechanical fraud detection methods with AI-driven collaborative counterfactual intervention systems. Machine learning models automatically analyze transaction patterns, predict customer archetypes, and detect selective omissions through computational algorithms, dramatically increasing detection speed while managing complexity through automated processing
Solution Approach 2:
The system changes detection parameters by using probabilistic archetype predictions and confidence scores instead of fixed rules. By adjusting detection thresholds and utilizing probabilistic reasoning, the system achieves high-speed detection of selective omissions while adapting to different customer behaviors and data sharing patterns
Data Source
AI summary
Systems, methods, and products for detection of selective omissions in an open data sharing computing platform comprises monitoring a plurality of events associated with a first digital record stored in a database of digital records, the first digital record uniquely identifying a first entity; associating a first detected event with a first set of words at least partially descriptive of the first detected event; associating a second detected event with a second set of words at least partially descriptive of the second detected event, the first event and the second event being detected, in response to digital records associated with the first event and the second event being shared over an open data sharing computing platform with express authorization provided by the first entity.