Thin-File Credit Risk Assessment Using Non-Credit Data Filters
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Financial service providers face difficulties in determining the creditworthiness of consumers with little or no credit history, making it challenging to assess their risk levels and offer credit accounts effectively.
Innovation Solution
A computing system analyzes demographic and non-credit data to identify thin-file records and develop multi-level filters that assess the likelihood of a consumer having a thin-file record and their associated credit risk, using existing transaction entries to differentiate between 'good' and 'bad' credit risks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional credit history analysis is used to assess consumer creditworthiness, then consumers with established credit history can be accurately evaluated, but consumers with little or no credit history (thin-file records) cannot be effectively assessed
Solution Approach 1:
The patent introduces an intermediary filtering system that processes consumer records through multiple stages. First, a thin-file filter identifies consumers with limited credit history using non-credit data variables. Then, a risk filter assesses their creditworthiness using alternative data points. This intermediary system bridges the gap between traditional credit analysis and thin-file consumers, enabling accurate assessment where direct credit history analysis fails.
Solution Approach 2:
The patent segments the consumer population into different groups based on credit file thickness. It creates separate assessment pathways: one for consumers with sufficient credit history (traditional scoring) and another for thin-file consumers (alternative data assessment). This segmentation allows the system to apply appropriate evaluation methods to each group, improving overall measurement precision while maintaining versatility.
2Reliability
If financial service providers restrict credit offerings to consumers with established credit history, then credit risk is minimized, but business growth opportunities are lost by excluding potential thin-file customers
Solution Approach 1:
The patent implements preliminary filtering and assessment actions before final credit decisions. The system pre-identifies thin-file consumers using non-credit data, pre-assesses their risk profiles using alternative variables, and pre-ranks them by creditworthiness. This preliminary action enables financial service providers to confidently extend credit to selected thin-file consumers, capturing business growth opportunities while maintaining risk control through advance evaluation.
Solution Approach 2:
The patent changes the assessment parameters from traditional credit history metrics to alternative non-credit data variables for thin-file consumers. Instead of relying on credit age, payment history, and debt ratios, the system uses employment data, rental payment history, utility payment records, and other alternative indicators. This parameter transformation enables reliable risk assessment for previously unevaluable consumers, balancing risk management with business expansion.
Data Source
AI summary
In some embodiments, systems and methods are disclosed for generating filters to determine whether a consumer is likely to have a scoreable credit record based on non-credit data, and to determine a potential risk level associated with an unscoreable credit record based on non-credit data. Existing scoreable and unscoreable records are compared to determine factors correlated with having an unscoreable record, and a multi-level filter is developed. Unscoreable records having at least one entry are compared to determine whether they are “good” or “bad” risks, factors correlated with either condition are determined, and a filter is developed. The filters can be applied to records comprising demographic data to determine consumers that are likely to have unscoreable records but represent good risks.


