Predictive Data Aggregation Engine for Real-Time Fraud Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Risk analysis systems in production computing environments face latency issues due to the need to retrieve and access large amounts of data from persistent databases, which hinders real-time fraud detection and decision-making processes.

Innovation Solution

Implementing a data aggregation engine that pre-calculates and stores data values and aggregations in a distributed computing system, allowing for faster and more efficient retrieval, reducing the reliance on persistent databases and minimizing latency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If data is retrieved from persistent databases for risk analysis, then comprehensive data availability is achieved, but data processing latency increases

Engineering Contradiction:

Improvedata availabilityVSAvoiddata processing latency

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

The system pre-calculates and stores data aggregations in a distributed computing system before they are needed for risk analysis. This preliminary computation of statistical summaries and data values eliminates the need to query persistent databases in real-time, thereby reducing latency while maintaining data availability.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

A distributed computing system acts as an intermediary between the persistent databases and the risk analysis system. This intermediary layer stores pre-computed data aggregations and serves the risk analysis system, decoupling the real-time analysis from the slower persistent database queries and reducing overall processing latency.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Speed

If pre-calculated data aggregations are stored in a distributed computing system, then data retrieval speed improves, but system complexity increases

Engineering Contradiction:

Improvedata retrieval speedVSAvoidsystem architecture complexity

Core Design Contradiction:

SpeedVSDevice complexity

Solution Approach 1:

The system divides the data storage and processing into segmented components: a distributed computing system for pre-computation and storage, and a risk analysis system for consumption. This segmentation allows each component to be optimized independently and simplifies the overall architecture by separating concerns.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system creates copies of data aggregations in the distributed computing system rather than working directly with the original persistent database. These copies are pre-computed and stored, allowing fast retrieval without adding complex real-time computation logic to the risk analysis system.

Inventive Principle:

Principle #26Copying

Data Source

PatentUS20220083877A1Predictive data aggregations for real-time detection of anomalous data

Publication Date: 2022.03.17 PAYPAL INC

AI summary

There are provided systems and methods for predictive data aggregations for real-time detection of anomalous data. A service provider, such as an electronic transaction processor for digital transactions, may access feature data for accounts prior to the feature data being used in a live risk analysis system, for example, at a designated time and/or for a designated time period. The service provider may predetermine data values from the feature data, such as aggregates of the feature data that are for certain time periods and utilized by the live risk analysis system. This processing may be done in a batch processing job in order to determine data values for multiple accounts. These data values are prestored in an available database for a distributed computing system of the service provider. Thereafter, when the live risk analysis system requires the data values, the data values may be immediately retrieved.