The secret bias hidden in mortgage-approval algorithms

EMMANUEL MARTINEZ and LAUREN KIRCHNER
The Markup

The new four-bedroom house in Charlotte, North Carolina, was Crystal Marie and Eskias McDaniels’ personal American dream, the reason they had moved to this Southern town from pricey Los Angeles a few years ago.

A lush, long lawn, 2,700 square feet of living space, a neighborhood pool and play- ground for their son, Nazret. All for $375,000.

Prequalifying for the mort- gage was a breeze. They said they had saved much more than they would need for the down payment, had very good credit — scores of 805 and 725 — and earned roughly six figures each, she in marketing at a utility company and Eskias representing a phar- maceutical company. The monthly mortgage payment was less than they’d paid for rent in Los Angeles for years.

They were scheduled to sign the mortgage documents on Aug. 23, 2019 — a Friday — and were so excited to move in they booked movers for the same day.

The Wednesday before the big day, the loan officer called Crystal Marie, and everything changed, she said: The deal wasn’t going to close.

The loan officer told the couple he had submitted the application internally to the underwriting department for approval a dozen, 15, maybe 17 times, getting a “no” each time. The couple had spent $6,000 in fees and deposits — all nonrefundable.

“It seemed like it was get- ting rejected by an algorithm,” she said, “and then there was a person who could step in and decide to override that or not.”

She was told she didn’t qualify because she was a contractor, not a full-time employee — even though her boss told the lender she was not at risk of losing her job. Her co-workers were contrac- tors, too, and they had mortgages.

Crystal Marie’s co-workers are white. She and Eskias are Black.

“I think it would be really naive for someone like myself to not consider that race played a role in the process,” she said.

An investigation by The Markup has found that lenders in 2019 were more likely to deny home loans to people of color than to white people with similar financial characteristics — even when we controlled for newly available financial factors the mortgage industry for years has said would explain racial disparities in lending.

—

This story was reported by The Markup, and the story and data were distributed by The Associated Press.

—

Holding 17 different factors steady in a complex statistical analysis of more than 2 million conventional mortgage applications for home purchases, we found that lenders were 40% more likely to turn down Latino applicants for loans, 50% more likely to deny Asian/Pacific Islander applicants, and 70% more likely to deny Native American applicants than similar white applicants. Lenders were 80% more likely to reject Black applicants than similar white applicants. These are national rates.

In every case, the prospective borrowers of color looked almost exactly the same on paper as the white applicants, except for their race.

The industry had criticized previous similar analyses for not including financial factors they said would explain disparities in lending rates but were not public at the time: debts as a percentage of income, how much of the property’s assessed worth the person is asking to borrow, and the applicant’s credit score.

The first two are now public in the Home Mortgage Disclosure Act data. Including these financial data points in our analysis not only failed to eliminate racial disparities in loan denials, it highlighted new, devastating ones.

We found that lenders gave fewer loans to Black applicants than white applicants even when their incomes were high — $100,000 a year or more — and had the same debt ratios. In fact, high-earning Black applicants with less debt were rejected more often than high-earning white appli- cants who have more debt.

“Lenders used to tell us, ‘It’s because you don’t have the lending profiles; the ethno- racial differences would go away if you had them,’” said José Loya, assistant professor of urban planning at UCLA who has studied public mortgage data extensively and reviewed our methodology. “Your work shows that’s not true.”

We sent our complete analysis to industry representatives: The American Bankers Association, The Mortgage Bankers Association, The Community Home Lenders Association, and The Credit Union National Association. They all criticized it generally, saying the public data is not complete enough to draw conclusions, but did not point to any flaws in our computations.

Blair Bernstein, director of public relations for the ABA, acknowledged that our analysis showed disparities but that “given the limitations” in the public data we used, “the numbers are not sufficient on their own to explain why those disparities exist.”

In written statements, the ABA and MBA criticized The Markup’s analysis for not including credit scores and for focusing on conventional loans only and not including government loans, such as those guaranteed by the Federal Housing Administration and Department of Veterans Affairs.

Isolating conventional loans from government loans is common in mortgage research because they are different products, with different thresholds for approval and loan terms. Government loans bring people who wouldn’t otherwise qualify into the market but tend to be more expensive for the borrower.

Even the Federal Reserve and Consumer Financial Protection Bureau, the agency that releases mortgage data, separate conventional and FHA loans in their research on lending disparities. Authors of one academic study out of Northeastern and George Washington universities said they focus on conventional loans only because FHA loans have “long been implemented in a manner that promotes segregation.”

As for credit scores, it was impossible for us to include them in our analysis because the CFPB strips them from public view from HMDA data — in part due to the mortgage industry’s lobbying to remove them, citing borrower privacy.

When the CFPB first proposed expanding mortgage data collection to include the very data that industry trade groups have told us is vital for doing this type of analysis — credit scores, debt-to-income ratio, and loan-to-value ratio — those same groups objected. They didn’t want the government to even collect the data, let alone make it public. They cited the risk of a cyber- attack, which could reveal borrowers’ private information.

“These new (data) fields include confidential financial data,” several large trade groups wrote in a letter to the CFPB, including the ABA and MBA. “Consequently, if this (sic) data are inadvertently or knowingly released to the public, the harm associated with re-identification would be even greater.”

Government regulators do have access to credit scores. The CFPB analyzed 2019 HMDA data and found that accounting for credit scores does not eliminate lending disparities for people of color.

In addition to finding disparities in loan denials nationally, we examined cities and towns across the country individually and found disparities in 89 metropolitan areas spanning every region of the country. In Charlotte, where Crystal Marie and her family searched for a home, lenders were 50% more likely to deny loans to Black applicants than white ones with similar financial profiles. In other places, the gap was even larger.

Black applicants in Chicago were 150% more likely to be denied by financial institutions than similar white applicants there. Lenders were more than 200% more likely to reject Latino applicants than white applicants in Waco, Texas, and to reject Asian and Pacific Islander applicants than white ones in Port St. Lucie, Florida. And Native American applicants in Minneapolis were 100% more likely to be denied by financial institutions than similar white applicants there.

“It’s something that we have a very painful history with,” said Alderman Matt Martin, who represents Chicago’s 47th Ward.

“Redlining,” the now-out- lawed practice of branding certain Black and immigrant neighborhoods too risky for financial investments that began in the 1930s, can be traced back to Chicago. Chicago activists exposed that banks were still redlining in the 1970s, leading to the establishment of the Home Mortgage Disclosure Act, the law mandating the collection of data used for this story.

“When you see that maybe the tactics are different now, but the outcomes are substantially similar,” Martin added, “it’s just not something we can continue to tolerate.”

Who makes these loan deci- sions? Officially, lending officers at each institution. In reality, software, most of it mandated by a pair of quasi-governmental agencies.

Freddie Mac and Fannie Mae were founded by the federal government to spur homeownership and now buy about half of all mortgages in America. If they don’t approve a loan, the lenders are on their own if the borrower skips out.

And that power means Fannie and Freddie essentially set the rules for the industry, starting from the very beginning of the mortgage-approval process.

Fannie and Freddie require lenders to use a particular credit scoring algorithm, “Classic FICO,” to determine whether an applicant meets the minimum threshold nec- essary to even be considered for a conventional mortgage, currently a score of 620.

This algorithm was developed from data from the 1990s and is more than 15 years old. It’s widely considered detrimental to people of color because it rewards traditional credit, to which white Americans have more access. It does not consider, among other things, on-time payments for rent, utilities, and cellphone bills — but will lower people’s scores if they get behind on them and are sent to debt collectors. Unlike more recent models, it penalizes people for past medical debt even if it’s since been paid.

“This is how structural racism works,” said Chi Chi Wu, a staff attorney at the National Consumer Law Center. “This is how racism gets embedded into institu- tions and policies and practices with absolutely no animus at all.”

Potentially fairer credit models have existed for years. A recent study by Vantage Score — a credit model developed by the “Big Three” credit bureaus to compete with FICO — estimated that its model would provide credit to 37 million Americans who have no scores under FICO models. Almost a third of them would be Black or Latino.

Yet Fannie and Freddie have resisted a steady stream of plaintive requests since 2014 from advocates, the mortgage and housing industries, and Congress to update to a newer model. Even the company that created Classic FICO has lobbied for the agencies to adopt a newer version, which it said expands credit to more people.

“A lot of things that minorities and underserved borrowers are doing, responsible financial behaviors, are going under the radar,” said Scott Olson, executive direc- tor of CHLA, a trade group representing small and mid- sized independent mortgage lenders.

Fannie’s and Freddie’s regulator and conservator, the Federal Housing Finance Agency, continues to allow the companies to stick with Classic FICO, more than five years after ordering them to study the effects of switching to something newer. The FHFA has also expressed concern about the “cost and operational implications” if they would have to continu- ally test new credit scoring models.

Neither of the companies would answer questions from The Markup about why they still require Classic FICO.