Search VantageScore.com
THE SCORE
 

Amidst a Slow News Cycle, VantageScore 4.0 Emerges

Dear Colleague:

Since there hasn’t been much going on in the news over the past several months – let’s call it a little over 100 days – we here at VantageScore decided that it would be a good time to fill the void with the announcement of a new credit scoring model.

We announced VantageScore 4.0 on April 3, and plenty of otherwise undistracted reporters wrote about it and what makes our new model different from other scoring models. Although the new model doesn’t officially go live until the fall, when it does, consumers and financial institutions will find that it truly breaks new ground.

But don’t take my word for it.

Credit.com’s Miles Ma wrote about VantageScore 4.0 in an April 5 article titled, “A New Credit Scoring Model Is On the Way: Here’s What to Expect.” He noted that, “A new credit scoring model — expected to roll out in fall 2017 — aims to more accurately measure credit risk by using more historical data and machine-learning techniques, while culling less reliable information.”

Ma went on to quote our own Sarah Davies, VantageScore’s senior vice president of research, product management and analytics. She spoke about how the new model excludes certain types of public records. “In all likelihood,” she said, “almost all civil judgments will be removed from credit files and a substantial portion of tax liens will be removed from credit files.”

Matt Shultz, writing for U.S. News & World Report, also covered VantageScore 4.0 in his May 8 article, “Here’s What VantageScore’s New Credit-Scoring Formula Means for Your Wallet.” He did a nice job of explaining the true impact of the new score’s use of trended data:

“Say you’re about to apply for a mortgage and have about $5,000 in credit card debt. If you once had $10,000 in debt but have diligently chipped away at it in recent months – paying on time, every time – and gotten that debt down to just $5,000, the scoring formula will likely reward you for your efforts. That downward trajectory for your debt makes you look more responsible and less risky to the formula. On the flip side, the formula won’t take as kindly to that $5,000 in debt if it has instead grown from just $500 in recent months. The formula will view that as a danger sign and may ding your score accordingly.”

“VantageScore 4.0 aims to ensure that lenders can be more, not less, confident in their forecasts.” – Automotive News, Hannah Lutz

Automotive News’ Hannah Lutz helped explain the changes in context of the credit industry as a whole, as well as the particular impact the model will have on auto lending. In her article, “Taking the sting out of less data for credit scores,” she writes, “With changes coming July 1 that limit what consumer information credit bureaus examine and monitor, concerns have grown whether credit scores might become more rosy and less reliable — which in turn might prompt skittish lenders to pull back from auto loans, at least until they become comfortable with the new scores. VantageScore 4.0, the company’s revised scoring model, incorporates those July 1 changes. It aims to ensure that lenders can be more, not less, confident in their forecasts of delinquencies and such.”

There’s more where that came from. Here are a few more stories in the press:

You can also learn more about VantageScore 4.0 here.

Have a VantageScore story, question or comment you’d like to share? Give us a shout on Twitter or Facebook.

Thanks,

Barrett

VantageScore 4.0:
Rise of the Machine… Learning

It’s been the Catch 22 of credit: Consumers who aren’t continually active users of credit struggle to get approved for new credit accounts.

For years, consumers who didn’t have a recent track record of credit cards, loans or other types of borrowing were either frozen out of getting a loan altogether, forced to pay higher interest rates or required to turn to other alternatives, such as pawn shops or payday lenders.

VantageScore 3.0, the most recent commercially available VantageScore model, scores up to 30-35 million consumers who can’t obtain a credit score under the older, conventional scoring models used by many financial institutions, including all mortgage lenders. The recently announced VantageScore 4.0 model, which will be commercially available this fall, applies the latest in computer-driven, machine-learning technology to drive additional predictive performance within this population of consumers.

Specifically, VantageScore 4.0 leverages this technique to generate a more predictive credit score among those who have not engaged in credit activity in the past six months, but have relevant information in their credit file that is more than six months old.

Data scientists at VantageScore used machine learning to take an even deeper dive into the credit histories of these consumers who are often overlooked by lenders. They examined a large number of specific details within credit reports to identify additional patterns that correspond with good financial behavior or increased risk.

“These consumers may not be high-frequency users of credit; and more importantly, have not engaged in credit activity in the last six months,” explains Nick Rose, one of the principal scientists for VantageScore. “Their credit use tends to be sporadic. For example, they might open an account for a few months, and then not use it again. If you try to score them with the conventional credit-scoring techniques, you can’t get any meaningful insight based on their credit usage and patterns.”

Indeed, although it’s relatively easy to predict the creditworthiness of a borrower who has had a mortgage for several years, as well as car loans, credit cards or other installment debt, analyzing and predicting the credit behavior of consumers with less recent credit histories called for a more technical solution.

“Machine learning found some 50,000 different relationships worth considering,” said Rose. “We took those 50,000 and reduced it to 300 potential relationships we could focus on to determine which ones were the most valuable and predictive,” Rose says.

For example, the machine learning approach helped data scientists assign default rate profiles based on the relationship between the balances on collection accounts, the ages of the collection accounts and the numbers of inquiries that those consumers had recently made.

Importantly, attributes that were discovered with this approach also adhere to certain standards for inclusion into a generic credit scoring model, such as ability to translate the attributes into predictive reason codes.

“The use of machine learning provided a significant performance boost within a key population,” said Rose. “And equally important is that we were able to incorporate our findings into the confines of a regulatory compliant, generic credit scoring model that lenders can implement into their current systems.”

What Are Credit Scores Actually Designed to Do?

Credit scores have become a ubiquitous and valuable component of lending and borrowing. They revolutionized underwriting by streamlining the process and permitting centralized lending, where a policy can be deployed with ease across a bank’s entire network of branches. But the one question that lenders that use scores, or consumers who are trying to improve theirs rarely asked is, “What is a credit score actually designed to do?”

Depending on whom you believe, credit scores were created to do a few different things. Some say they are designed to predict default, bankruptcy or some other form of non-performance. Others believe that credit scores are designed to predict whether or not you can afford the loan or credit card for which you’ve applied.

Some point out that credit scores have served to end some forms of racial, religious or gender discrimination (both intentional and unintentional) that were not uncommon during the earlier era of manual underwriting.

To the cynical bunch, however, credit scores are designed to reward people for being in debt.

All of the aforementioned answers are wrong. Credit scores aren’t “designed” to do any of those things.

All credit-scoring systems have what’s formally referred to as a “performance definition.” A performance definition is the model’s stated design objective or principal intended purpose. And although credit scores certainly may do more than just assess consumer credit risk, there is a best practice for the use of credit scores (like using a butter knife rather than a steak knife to cut a steak).

Credit-bureau-based scoring systems — the models that are based on the data in one of your credit reports with the three major bureaus — are designed to predict the likelihood that you’ll go 90 days (or more) past due on any obligation in the 24-month period after your score has been calculated. That is their performance definition, and that is why these credit scores can take a considerable hit if you’ve gone 90 days (or more) past due on a credit obligation.

Now, this limited performance definition doesn’t mean that such credit scores are unable to help predict the likelihood that you’ll file for bankruptcy. It just means that these scores weren’t “tuned” to predict that particular outcome. But just like the butter knife and steak analogy, such scores may still be effective in measuring other types of risks.

This is also why your credit scores don’t take the same hit if you have an isolated 30-day late payment on your credit reports (especially relative to the hit you would take for a more severe delinquency, or even some form or evidence of default, like a third-party collection suddenly appearing on your credit reports). It’s also the reason why other incidents, like charge-offs, settlements, repossessions, foreclosures or other severely derogatory credit entries, tend to have the same, or very similar, adverse effects on your scores. Such events all represent accounts that are 90 days (or more) past due.

If you have low-level or no delinquencies on your credit reports, then you’ve proven to the credit scoring system that you’re not willing to go 90 days past due on anything, and your scores are rewarded as a result. However, if you do have a record of going 90 days or more past due, your scores will never be as high as they otherwise could be.

The Credit World Descends on Austin

A few weeks ago, card and payment executives at the industry’s leading issuers, networks and retailers conference gathered in Austin for a deep dive into what the future holds for the world of consumer credit risk management. The three-day-long Card Forum, presented by SourceMedia (publisher of American Banker) and sponsored by VantageScore, featured presentations on myriad topics, with a particular focus on what’s next for the industry.

As “The Times They Are A-Changin’” played behind him, VantageScore Solutions CEO Barrett Burns opened the event’s Consumer Credit Summit – essentially a conference within the conference—which was attended by a who’s who of the credit bureau, issuer and media worlds.

“Bob Dylan’s lyrics are as relevant today as they ever were…be it in our politics or our industries. Dare I say they are relevant to our discussions today as well,” he said. “Today we’re all about helping you prepare for change. You’ll hear about the online consumer voice and its impact on wallet share, how consumers choose to spend their money these days, and how a generation of tech-savvy millennials are in need of new ways to educate themselves on finance and credit.”

The Consumer Credit Summit featured sessions helmed by a variety of industry leaders, including:

  • How Millennials Think About Money – Steve Rice, Executive Vice President, Financial Education, EverFi
  • The Evolution of the Consumer Card Wallet – Nidhi Verma, Senior Director, Financial Services Research and Industry Insights, TransUnion & Tamer El-Rayess, Chairman, Continental Finance
  • How Well Are Card Issuers Connecting With Consumers Online? – Jeanine Skowronski, Executive Editor, Credit.com, Amanda Abella, Author, AmandaAbella.com, Jason Steele, Author, JasonSteele.com & Penny Crosman, Editor at Large, American Banker
  • How Can Issuers Build Their New Customer Base & Create More Value For Cardholders? – Christopher Speltz, Chief Executive Officer, Bankrate Credit Cards & CreditCards.com
  • Multi-Bureau Panel Discussion – Paul C. Siegfried, Senior Vice President, Financial Services, Card Business Leader, TransUnion, Ankush Tewari, Senior Director of Market Planning, LexisNexis Risk Solutions, Chris Moss, Senior Director, Product Management, Equifax & Mike Trapanese, SVP, Strategy and Alliances, VantageScore

During the Multi-Bureau Panel session, participants discussed the incorporation of machine learning into the credit business. It was suggested that this incorporation is the key to the ongoing development of more predictive models for populations who have traditionally been underserved by the financial services industry. Machine learning can also assist with the identification of fraud ahead of time. Panelists also discussed the increased use of alternative data sources and how that data is now being used to generate more holistic consumer profiles.

Other presenters and attendees included representatives of Chase, Wells Fargo, Bank of America, Google, U.S. Bank, PayPal, RBC, Visa and many others.

Five Questions with William D. Cohan

Did you know“Dodd-Frank occurred because people – including many of our elected representatives – don’t understand how Wall Street really works.” – William D. Cohan

William David Cohan is The New York Times best-selling author of three non-fiction books, including his most recent hits, Why Wall Street Matters and Wall Street: Money and Power: How Goldman Sachs Came to Rule the World. A former senior Wall Street M&A investment banker for 17 years, he is a contributing editor at Vanity Fair, and writes a weekly opinion column for BloombergView. He also writes for The Financial Times, Bloomberg BusinessWeek, The Atlantic, the Washington Post and the New York Times Magazine.

In your most recent book, “Why Wall Street Matters,” and in a number of interviews, you’ve contended that regulation – Dodd-Frank in particular – went too far and is now stifling the flow of funding to smaller businesses. At the same time, there has been a feeling that the Justice Department did not go far enough in terms of prosecuting criminal cases after the financial crisis. What is behind this juxtaposition?

These are not mutually exclusive ideas. Both things can be true. It is a verifiable fact that the Justice Department, under Obama, failed to meaningfully hold Wall Street traders, bankers and executives responsible for the wrongdoing that occurred on Wall Street in the years leading up to the 2008 financial crisis. Why it failed to do this is one of the biggest unanswered questions of the crisis and its aftermath. As for Dodd-Frank, it’s a piece of legislation, which in my view, occurred because people – including many of our elected representatives – don’t understand how Wall Street really works. If Congress just focused on incentives and how people on Wall Street are rewarded, then writing a short piece of legislation to change the behavior on Wall Street wouldn’t be so difficult. I wrote Why Wall Street Matters as much for people in Congress (and the White House) as for the American people. I can only hope and pray that a few more of them read it.

Many readers of this newsletter are consumers, consumer advocates or regulators, many of whom have been harsh critics of Wall Street’s practices. What role does Wall Street play in their daily lives, and more specifically, what did Wall Street have to do with the movie, Beauty and the Beast?

Wall Street is integral to our lives. There are so many things we take for granted — the iPhone, stocked supermarket shelves, gasoline for our cars, heat for our homes, and so on — that would not be even remotely possible without the capital that Wall Street provides. Without Wall Street money, the Walt Disney Company wouldn’t be able to make a $100 million Beauty and the Beast movie. It would simply be inconceivable that Disney would spend that kind of money on one movie if it didn’t have access to Wall Street capital. So instead of trying to pretend that Wall Street is evil and responsible for every bad thing that happens in the world, let’s focus instead on fixing what is wrong with Wall Street and celebrating what it does right. That will be much more productive in the long run.

Before you became one of the country’s top financial writers and a best-selling author, you worked on Wall Street as a mergers and acquisitions specialist. Did you always have an itch to be a writer or was there something that caused you to change careers?

I had been a journalist before I worked on Wall Street. I am a 1983 graduate of the Columbia Graduate School of Journalism. Before that, I worked briefly for the Winchester Star, outside of Boston, and then the Washington County Post, in Salem, New York, where I was the editor and their only reporter.

After Columbia, I worked at the Raleigh Times, in Raleigh, North Carolina, as the education reporter for two years, where I won back-to-back statewide investigative reporting awards for revealing corruption in the school system. So I had a background in journalism, although I never thought I would return to journalism after I went to Wall Street.

“Why Wall Street Matters” is under 200 pagesm, and a great, quick read. Dodd-Frank is over 700 pages, and is anything but. Thoughts?

Well obviously, one is a book that people will hopefully want to buy, and the other is a piece of legislation, which is like a camel (a horse written by committee). Even worse, it was written by the two men who received some of the largest donations from the financial services industry. The original Glass-Steagall Act, which everyone waxes poetic about these days, was only 35 pages long. What we need is smart regulation that ties behavior on Wall Street directly to compensation. Dodd-Frank is a bureaucratic nightmare, although certain aspects are important to keep: higher capital requirements, lower leverage requirements and mandating that derivatives be traded on exchanges. As long as we change Wall Street’s compensation system as part of the bargain, most of the rest of it can be junked as far as I am concerned.

The term “Wall Street” broadly describes investment banking, asset management, etc., but also connotes that New York City is the industry’s global headquarters. Is New York City still the financial capital of the world, and is there risk that its competitiveness is being undermined?

Yes, Wall Street is still the global center of finance; in fact now as much as ever. Wall Street has never been stronger, as a relative matter, in the wake of the financial crisis. European and Asian banks are in disarray. Wall Street is both the intellectual and economic capital of finance and I don’t see that changing anytime soon. 

BACK TO TOP
Valued partners:
CBA MBA
VantageScore Licensees:
Equifax Experian TransUnion