Market Overview

VantageScore Research Examines Model for Statistical Bias Towards Minority and Newly Scoreable Consumers

Share:

Model passes thorough testing to ensure fair lending practices start
with an accurate and inclusive scoring model

VantageScore
Solutions
, LLC, developer of the VantageScore® credit scoring model,
released a new white paper "Testing
Credit Scoring Models for Statistical Bias: Ushering in a New Era of
Transparency"
which details, through rigorous testing, that the
VantageScore 4.0 credit scoring model does not produce any statistical
bias towards key population segments including minority groups and
consumers who are conventionally unscoreable but scoreable when the
VantageScore model is employed.

By using the industry-standard test called the Chi-Square tests, the
study shows how the latest VantageScore 4.0 credit scoring model evenly
distributes probability of default1 across population
segments and provides a methodology for best practices for lenders to
test their own models.

The VantageScore 4.0 statistical bias research shows that:

  • For both credit card and first mortgage loans, default curves are
    statistically aligned among ethnic groups at each credit score value
    among the overall population.
  • For all ethnic groups, there is near alignment of default curves,
    indicating an unbiased model.
  • For score bands with sufficient sample sizes, there is no discernible
    difference in the probability of default among consumers who are
    conventionally scored by credit score models (mainstream consumers)
    and the approximately 30 million consumers who are not conventionally
    scored in the credit industry (e.g., universe expansion consumers).
  • More broadly, credit scoring models can and should be publicly
    scrutinized for bias towards key population segments, including
    minority groups and those who do not exhibit traditional credit
    behaviors.

"In an age of equitability and accountability, we know it's important to
put the consumer first. This starts with thorough, continuous and public
testing on our models – whether it be for statistical bias or
performance. By holding ourselves accountable we maintain the confidence
of both consumers and lenders," said Barrett Burns, CEO and president,
VantageScore Solutions.

For test results and more details on the "Testing Credit Scoring Models
for Statistical Bias: Ushering in a New Era of Transparency" white
paper, visit: www.vantageScore.com/statbias18.

About VantageScore Solutions

Credit scores can impact many aspects of your life, everything from
whether you are able to get a loan and how much interest you will have
to pay to whether you are able to rent an apartment. At VantageScore, we
understand the impact credit scores have and we take it seriously.

VantageScore Solutions, LLC (www.VantageScore.com)
is the independently managed company that owns the intellectual property
rights to the VantageScore credit scoring models and is the leader in
scoring innovation. The recently introduced VantageScore 4.0 model
scores approximately 30 million consumers who typically are not scored
by conventional models – without sacrificing predictiveness.

VantageScore credit scores are used by lenders, landlords, utility
companies, telecom companies, and many others to determine
creditworthiness. In fact, a recent study found that more than 8.5
billion VantageScore credit scores were used in June 2016-July 2017 by
over 2,700 unique users. Of those, over 6 billion scores were used by
more than 2,200 lenders of all sizes in their lending processes and over
one billion VantageScore credit scores were provided directly to
consumers through dozens of websites and lenders who provide their users
and customers with their credit scores for free. By using the
VantageScore model, these enterprises have access to many more
consumers, and in turn, consumers have greater access to mainstream
credit.

While there are many credit scoring models in the industry, the
"win-win" for VantageScore is its innovative, highly predictive,
patent-protected, tri-bureau scoring methodology that provides lenders
and consumers with more consistent credit scores across all three
national credit reporting companies.

1 A metric that measures a consumer's likelihood to default
over a period of time.

View Comments and Join the Discussion!