Periodic Sequence Detection for Fraudulent Payment Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing fraud detection software in financial systems requires constant parameter tuning and human supervision, making it inefficient for quickly and accurately identifying fraudulent activities in large datasets spanning long periods.
Innovation Solution
A computerized method and system that automatically detects periodic sequences of payments by collecting and processing payment data, assigning payments to time phases, grouping them into clusters, and determining periodic sequences without human intervention, enabling quick and accurate detection of deviations from established patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If existing fraud detection software is used, then fraud detection capability is provided, but constant parameter tuning and human supervision are required, reducing productivity
Solution Approach 1:
The system automatically performs parameter tuning and fraud detection without requiring human supervision. The machine learning model self-adjusts parameters based on the data patterns it discovers, eliminating the need for constant manual intervention while maintaining reliable fraud detection capability.
Solution Approach 2:
The system pre-processes and analyzes historical payment data to establish baseline periodic patterns before fraud detection begins. This preliminary action creates a foundation of learned patterns that enable rapid automated detection without requiring manual parameter setup for each new dataset.
2Reliability
If existing fraud detection software is used, then fraud detection is performed, but close human supervision and manual review are needed, increasing device complexity
Solution Approach 1:
The system autonomously performs fraud detection by automatically comparing new transactions against learned periodic patterns. The machine learning model self-evaluates anomalies and generates fraud indicators without requiring manual review, simplifying system operation while maintaining detection accuracy.
Solution Approach 2:
The system continuously learns from detected patterns and adjusts its detection parameters based on feedback from analyzed transactions. This automated feedback loop replaces manual supervision by allowing the system to self-optimize its detection accuracy over time.
3Measurement precision
If manual parameter tuning is required, then detection accuracy can be adjusted, but constant tuning reduces speed of detection
Solution Approach 1:
The system performs comprehensive parameter optimization and pattern learning during an initial pre-processing phase. This preliminary action establishes accurate detection parameters in advance, enabling rapid real-time fraud detection without requiring ongoing manual tuning that would slow down the detection process.
Solution Approach 2:
The system dynamically adjusts detection parameters automatically based on the characteristics of the data being analyzed. The machine learning model adapts its sensitivity and detection thresholds in real-time based on learned patterns, maintaining high accuracy while enabling fast detection without manual intervention.
Data Source
AI summary
The present disclosure relates to systems, methods, and computer readable media for detecting periodic sequences of events. A computer-implemented method may include collecting processing times and values associated with each of a plurality of events. The method may also include assigning each of the plurality of events to at least one of a plurality of time phases, the plurality of time phases forming a period characteristic of the plurality of events. The method may also include grouping the events in each of the plurality of time phases into one or more clusters, based on the respective values associated with the events. The method may also include determining a periodic sequence of events based on the one or more clusters. The method may further include recording the periodic sequence of events in a database of periodic sequences.