Fraud Detection System Using Machine Learning Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems fail to effectively identify and prevent fraudulent payment transfers, leading to financial and reputational losses for individuals and companies.
Innovation Solution
A fraud detection system that uses a computing device to analyze data from previous payment transfers, generate a fraud detection value, and determine whether a payment transfer is fraudulent, allowing for real-time identification and potential prevention of fraudulent transactions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual verification of payment transfers is used, then fraud detection accuracy can be improved, but processing time and operational costs increase
Solution Approach 1:
The patent replaces manual verification processes with an automated computing device that performs fraud detection. The system automatically receives payment transfer data, analyzes it against established criteria, and generates fraud detection values without human intervention, thereby maintaining detection accuracy while eliminating time loss associated with manual processing.
Solution Approach 2:
The fraud detection system operates autonomously by self-evaluating payment transfer data against predefined fraud criteria. The computing device automatically processes transactions, generates fraud detection values, and flags suspicious transfers without requiring external verification, enabling the system to serve itself in detecting fraud while maintaining speed and accuracy.
2Reliability
If comprehensive fraud analysis is performed on all payment transfers, then fraud detection reliability is improved, but system complexity and computational resources increase
Solution Approach 1:
The fraud detection system segments the analysis process into distinct components: receiving payment transfer data, analyzing against specific fraud criteria, generating fraud detection values, and flagging suspicious transfers. This segmentation allows comprehensive fraud analysis to be performed systematically without overwhelming system complexity, as each segment handles a specific aspect of the analysis independently.
Solution Approach 2:
The system changes parameters by establishing specific fraud detection criteria and thresholds that transform complex fraud analysis into measurable, comparable values. By converting fraud assessment into quantifiable fraud detection values with defined thresholds, the system maintains high reliability while managing complexity through parameter standardization.
3Loss of energy
If real-time fraud detection is implemented, then financial losses are reduced, but processing speed may be compromised
Solution Approach 1:
The system performs preliminary fraud detection analysis as payment transfer data is received, before the transaction is finalized. By proactively analyzing transactions in real-time and generating fraud detection values during the transfer process, the system prevents financial losses without compromising speed, as the detection occurs concurrently with transaction processing rather than as a subsequent review.
Data Source
AI summary
This application relates to apparatus and methods for identifying fraudulent payment transfers. In some examples, a computing device determines payment transfer initiation features, and payment transfer reception features, based on previous payment transfer data. The computing device may train a machine learning fraud detection model with the payment transfer initiation features, and may train a machine learning fraud detection model with the payment transfer reception features. Once trained, the computing device may employ the machine learning fraud detection models to identify fraudulent payment transfers. For example, the computing device may determine whether a payment transfer is fraudulent when the payment transfer is initiated. Assuming the payment transfer is allowed, the computing device may determine whether the payment transfer is fraudulent when the payment is being received. In some examples, the computing device prevents completion of the purchase transaction if the payment transfer is determined to be fraudulent.