The startup offers a peer-to-peer lending platform that connects borrowers with low or non-existent credit ratings directly to lenders through an alternative credit evaluation method. This platform enables underserved populations to access financial resources by providing a fair assessment that overcomes traditional credit assessment challenges.
Funding
$4.6M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Product
Problem
Traditional credit scoring systems often exclude individuals with limited or no prior financial transaction history, such as young adults, homemakers, and foreign nationals. This lack of financial data prevents these "thin filers" from accessing essential financial services, despite their potential creditworthiness.
Solution
CrePASS offers an alternative credit evaluation platform that leverages non-traditional, non-financial big data to assess the creditworthiness of individuals underserved by conventional scoring models. By analyzing digital records related to social activity, mobile usage, and online behavior, CrePASS provides a more comprehensive and nuanced evaluation of an applicant's repayment capacity. This approach enables financial institutions to extend services to a broader customer base while offering individuals with limited financial footprints access to fair and appropriate credit opportunities. The platform utilizes a cloud-based business service, STEPs (Scoring Technologies Enterprise Platform & Solutions), to facilitate real-time data processing for data collection, variable creation, variable selection, ML algorithm selection, and model verification.
Target Audience
CrePASS primarily targets financial institutions seeking to expand their customer base by reaching individuals with limited credit histories, as well as individuals who are currently excluded from traditional financial services due to a lack of conventional credit data.
Features
- Analyzes over 12,000 data points from mobile, email, and social media sources (with user consent) to evaluate creditworthiness.
- Employs machine learning algorithms, including Lasso Model and Greedy Forward Selection, to identify the most predictive variables.
- Generates over 300 variables representing relationships, psychology, and behavioral patterns to assess an applicant's willingness to repay.
- Utilizes non-linear transformations, normalization, and decision trees to identify outliers and interactions between variables.
- Performs stability diagnostics using cross-validation and out-of-sample testing to ensure model reliability.
- Offers a cloud-based platform (STEPS) for real-time data processing and analysis.