Anomaly Detection System Using Aggregated Third-Party Metrics

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems for monitoring a user's situation are limited in incorporating situations that do not conform to available information, particularly when dealing with anomalous events such as changes in income, assets, or physical moves, which can lead to inaccurate financial planning.

Innovation Solution

A system comprising a network communication interface and a memory device with a processing device that executes program code to determine anomalous situations, acquire aggregated metrics from third parties, and analyze these metrics to adjust the user's financial plan, using historical records of similar individuals to account for unforeseen changes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional monitoring systems use only current available information for analysis, then the system complexity remains low, but the accuracy of financial planning deteriorates when anomalous situations occur

Engineering Contradiction:

Improveaccuracy of financial planningVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by pre-acquiring and storing aggregated metrics from multiple third-party sources during normal periods. When an anomalous situation is detected, these pre-acquired metrics are immediately available for analysis, eliminating the need for complex real-time data gathering during crises and thereby maintaining both high accuracy and manageable system complexity.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary layer of aggregated metrics that mediate between raw third-party data and the financial planning analysis. This intermediary layer pre-processes and consolidates information from multiple sources, reducing the complexity of direct data analysis while improving the accuracy of anomaly detection and financial planning recommendations.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If the system incorporates aggregated metrics from third parties for anomalous situations, then the reliability of financial analysis improves, but the loss of time for data acquisition increases

Engineering Contradiction:

Improvereliability of financial analysisVSAvoidtime for data acquisition

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary data acquisition by continuously gathering and storing aggregated metrics from third-party sources before anomalous situations occur. This pre-positioning of data ensures that when anomalies are detected, the system can immediately access relevant historical metrics without time-consuming real-time data collection, thereby maintaining both high reliability and rapid response.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system dynamically adjusts its data acquisition strategy based on the detected anomaly type. For common anomaly patterns, it quickly retrieves pre-acquired metrics from storage. For novel or complex anomalies, it selectively acquires additional specific data. This dynamic approach optimizes the balance between reliability and time loss by adapting data gathering to the specific situation.

Inventive Principle:

Principle #15Dynamics

3Adaptability or versatility

If the system uses historical records of unrelated individuals to define aggregated metrics, then the adaptability to various anomalous situations improves, but the difficulty of detecting and measuring relevant information increases

Engineering Contradiction:

Improveadaptability to anomalous situationsVSAvoiddifficulty of finding relevant information

Core Design Contradiction:

Adaptability or versatilityVSDifficulty of detecting and measuring

Solution Approach 1:

The patent introduces an intermediary processing layer that automatically matches detected anomalous situations with relevant historical records from unrelated individuals. This intermediary matching system uses pattern recognition and classification algorithms to identify pertinent historical cases, thereby maintaining high adaptability to various anomalies while reducing the manual difficulty of finding relevant information through automated information retrieval and comparison.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS10460383B2System for transmission and use of aggregated metrics indicative of future customer circumstances

Publication Date: 2019.10.29 BANK OF AMERICA CORP

AI summary

A network communication interface and a memory device storing an anomaly application and a resource application are provided. A processing device is operatively coupled to the memory device, wherein the processing device is configured to execute computer-readable program code to: determine the existence of an anomalous situation for a user; initiate the anomaly application to acquire aggregated metrics from third parties associated with the anomalous situation; and analyze the anomalous situation using the aggregated information. The aggregated metrics may be obtained from the entity system and/or from a third party system. The aggregated metrics may comprise the historical financial record of a plurality of third parties. The aggregated metrics may be obtained by searching a datastore of the entity system for relevant information from a historical record of unrelated individuals.