Conventionally Unscoreable Population Grows to 40 Million Consumers
VantageScore study shows that outdated, conventional scoring models lead to an increase in marginalized consumers facing unfair hardships when applying for credit
VantageScore® Solutions, LLC, the company behind the VantageScore credit scoring models, released the results of an analysis that shows that the population of consumers who are conventionally unscoreable (i.e., those who fail to meet the minimum scoring requirements of widely used conventional credit scoring models) has grown from approximately 30-35 million in 2010 to approximately 40 million in 2018.
Through no fault of their own, these consumers would fail to meet the requirements for automated underwriting processes widely used across the consumer lending system and could either be turned down for loans or face potentially unfair pricing and terms.
To perform the analysis, VantageScore used a random, anonymous sample of 15 million consumer credit files obtained from the three nationwide credit bureaus and calculated the proportions of the consumers that would satisfy conventional model scoring requirements or fall into one of the four groups of conventionally unscoreable consumers – new to market, infrequent credit user, rare credit user or no accounts. The proportions were then applied to the overall US adult population based on 2017 US Census figures to estimate the total population of conventionally unscoreable consumers. Further, leveraging the 2017 American Community Survey published by the US Census Bureau, VantageScore estimated the impact on different ethnicities using zip code level data.
The analysis shows that based on the 2010 U.S. Census, the overall population was 309 million, of which 30-35 million were unscoreable when conventional models were used by lenders. These consumers could be scored with the VantageScore model.
As the overall U.S. population has increased, so has the number of consumers who cannot be scored by conventional credit scoring models. According to the latest 2017 U.S. Census, the overall population grew to 326 million and the number of conventionally unscoreable consumers who can now be scored with the VantageScore 4.0 model increased to approximately 40 million.
Overall, the proportion of the adult population that is conventionally unscoreable remains unchanged at close to 16 percent.
The ability to safely, soundly and accurately score these consumers represents an opportunity to make credit markets more accessible to additional consumers who have been historically underserved. Despite advances in data availability, granularity and modeling architecture, which in turn have led to the ability to assess risk on a larger pool of consumers, many credit decisions including almost every single mortgage application continue to rely on models that put these consumers at a possible disadvantage.
A breakdown of the conventionally unscoreables consumers that can be scored with the VantageScore model includes:
| “New to Market” | Young to credit, emerging borrower | Consumers who only have credit accounts that are less than 6 months in age |
| “Infrequent” or “Rare”
Credit users |
Dormant credit use | Consumers who haven’t had an update/reporting on their credit files in the past 6 months but have had updates more than 6 months ago |
| “No Trades” | Have only external collections, public records and inquiries on their file | Consumers who have no tradelines but are scored based on the external collections and public records on their file |
The breakdown of the conventionally unscoreable population by ethnicity includes:
| 2018 Unscoreables – All Scores | 2018 Unscoreables – Scores 620+ | |
| Total | 40 million | 10.06 million |
| Black and Hispanic | 12.2 million | 2.4 million |
| Asian/Pacific-Islander | 1.6 million | <1 million |
| White | 25.7 million | 7 million |
| Native American | 335,000 | 66,000 |
Below is a map that shows the percentage of consumers within each state who are considered unscoreable (click on the map to enlarge image):
“Using a model that can accurately score a greater proportion of the adult population in the United States can improve a lender’s bottom line, while at the same time, level the playing field for consumers who have been historically marginalized,” said Barrett Burns, president & CEO of VantageScore Solutions. “The borrowers of today and those entering the phase of their lives where accessing credit is critical aren’t behaving as consumers did a decade ago, and to effectively lend to them requires a new approach to credit scoring.”
Introduced in October of 2017, VantageScore 4.0 uniquely uses machine learning techniques in the development of scorecards for consumers who are conventionally unscoreable. VantageScore 4.0 also leverages trended credit data attributes to drive predictive lift and provide greater accuracy in the assessment of a consumer’s creditworthiness.
Popular Articles
Consumer FAQ: Benefits of Adding Rent and Utility Data to a Credit File
Advantage of Adding Rent and Utility Data whitepaper
Credit with a Conscience fact sheet
Driving Financial Inclusion with Data and Analytics fact sheet