Demographic Address Analysis for Identity Theft Risk Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for detecting identity theft in account fraud, such as address changes and new account applications, are inadequate as they rely on negative databases and verification techniques that can be manipulated by criminals, often failing to detect fraud when delivery addresses are not included in these databases.
Innovation Solution
A system and method that analyze demographic data associated with street addresses to assess the risk of identity theft fraud by comparing old and new addresses, using a scoring formula to predict the likelihood of fraud, incorporating data from various sources like credit bureaus, USPS, and known fraud addresses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional negative database methods are used to detect identity theft, then known fraud addresses can be identified, but delivery addresses not included in the database cannot be detected and false positives increase
Solution Approach 1:
The patent transitions from checking addresses against a negative database (one-dimensional lookup) to analyzing multiple demographic dimensions (income, education, household composition, tenure) simultaneously. This dimensional expansion allows detection of fraudulent addresses without requiring complete database coverage, as fraud is detected through demographic inconsistencies rather than simple presence/absence in a database.
Solution Approach 2:
The patent changes the detection parameters from binary database matching (address in database or not) to continuous demographic variable analysis (income levels, education levels, household size, tenure). By transforming the detection mechanism into analyzing multiple demographic parameters and their consistency, the system achieves reliable fraud detection without requiring exhaustive database coverage.
2Reliability
If demographic data analysis is performed on address changes and new accounts, then fraud risk can be predicted, but data processing complexity and computational requirements increase
Solution Approach 1:
The patent segments the fraud detection process into distinct modules: demographic data collection, demographic variable analysis, consistency checking, and risk scoring. Each module handles a specific aspect of the analysis, making the overall complex system manageable and maintainable. The segmentation allows parallel processing of different demographic factors and simplifies the integration of multiple data sources.
Solution Approach 2:
The patent introduces demographic consistency analysis as an intermediary layer between raw address data and fraud determination. Instead of directly comparing addresses against fraud databases, the system uses demographic variables as intermediaries to indirectly assess fraud risk. This intermediary approach transforms the complex problem of fraud detection into a series of simpler consistency checks.
3Measurement precision
If verification of application data elements is performed using independent data sources, then identity can be corroborated, but the process only verifies stolen information and cannot detect new fraud
Solution Approach 1:
The patent inverts the traditional verification approach instead of trying to prove identity is legitimate through data matching, it assumes fraud and looks for demographic inconsistencies that indicate fraudulent activity. Rather than verifying the applicant's story against external sources, the system analyzes whether the demographic profile at the address is consistent with what would be expected for a legitimate resident, turning verification into inconsistency detection.
Data Source
AI summary
In one embodiment, this invention analyzes demographic data that is associated with a specific street address when presented as an address change on an existing account or an address included on a new account application when that address is different from the reference address (e.g., a credit bureau type header data). The old or reference address and the new address, the new account application address or fulfillment address demographic attributes are gathered, analyzed, compared for divergence and scaled to reflect the relative fraud risk.