Can Your Facebook Profile Help Determine Whether You Get a Mortgage?

It could if your lender is one of a growing number using innovative ways to assess customers’ creditworthiness.

National Journal
Nancy Cook
June 4, 2014, 8:08 a.m.

Sci­ent­ists and math­em­aticians comb through roughly 950 dif­fer­ent data points when cal­cu­lat­ing an Amer­ic­an con­sumer’s cred­it score, the all-im­port­ant num­ber that can de­term­ine an in­di­vidu­al’s pur­chas­ing power on everything from an auto loan to a home mort­gage. But only about 15 per­cent of those data points can ac­tu­ally pre­dict the prob­ab­il­ity that a per­son will pay back her debt. The ma­jor cred­it re­port­ing bur­eaus are con­stantly tweak­ing the mix they ex­am­ine to give them­selves the most cur­rent snap­shot of con­sumer spend­ing and debt.

Shift­ing through and mod­el­ing this data is the chief aim of Vant­ageScore, a 10-per­son, Con­necti­c­ut-based star­tup foun­ded in 2006. One of the goals of Vant­ageScore is to eval­u­ate a great­er por­tion of the pop­u­la­tion and, by ex­ten­sion, give more people ac­cess to cred­it. The com­pany es­tim­ates that its latest 3.0 mod­el al­lows it to score at least 27 mil­lion new con­sumers, a group lar­ger than the pop­u­la­tion of Texas. “I look at the cred­it score as a gate­way,” says Bar­rett Burns, pres­id­ent and CEO of Vant­ageScore Solu­tions. “Our main mis­sion is to cre­ate the op­por­tun­ity for people to have ac­cess to re­spons­ible cred­it. Even if a per­son gets a lousy score — if you do not know what your score is, then you do not know how to change your be­ha­vi­or.”

Ac­cess to cred­it now con­sumes much of the dis­cus­sion sur­round­ing the hous­ing mar­ket, which has not re­boun­ded as fast as eco­nom­ists had hoped fol­low­ing the glob­al fin­an­cial re­ces­sion. Scores of first-time home buy­ers, who typ­ic­ally make up about 40 per­cent of home sales, re­main locked out of the mar­ket thanks to more strin­gent lend­ing re­quire­ments. If mort­gage lenders dropped the re­quired cred­it score by just 50 points (on par with prere­ces­sion lend­ing), then 12 mil­lion more people could gain cred­it and po­ten­tially pur­chase homes, ac­cord­ing to a re­cent ana­lys­is by Mark Zandi, chief eco­nom­ist for Moody’s Ana­lyt­ics. “It is dif­fi­cult to see how the eco­nomy can achieve full em­ploy­ment over the next few years un­less hous­ing leads the way,” Zandi wrote in a May re­search note.

Vant­ageScore is not the only com­pany to look for dif­fer­ent ways to eval­u­ate con­sumers’ cred­it­wor­thi­ness. Ex­peri­an, one of the three big cred­it re­port­ing bur­eaus, pur­chased a small com­pany in 2010 to al­low it to track rent­al pay­ments as a way to meas­ure a per­son’s like­li­hood to pay off debt. A hand­ful of fin­an­cial star­tups have also entered the mix; one uses in­form­a­tion from a con­sumer’s so­cial-me­dia feeds, com­bined with private data from the cred­it bur­eaus, to de­term­ine a per­son’s cred­it­wor­thi­ness. With­in the in­dustry, there’s talk of lean­ing on a pay­ment as simple as a cell-phone bill or a per­son’s re­mit­tances to his home coun­try to factor in­to the almighty cal­cu­la­tion of the cred­it score.

The prob­lem with these dif­fer­ent meas­ure­ments? They all look to the past without pre­dict­ing a con­sumer’s abil­ity to pay off debt in the fu­ture, says An­namaria Lusardi, a pro­fess­or at the George Wash­ing­ton Uni­versity School of Busi­ness and per­son­al-fin­ance ex­pert. “We need a way to think about people’s po­ten­tial,” she says. “The prob­lem with hav­ing a stat­ic view is that just be­cause a per­son, as an ex­ample, might be un­em­ployed now does not mean that he will be un­em­ployed in 30 years.”

Far bet­ter, Lusardi says, would be to in­stead ex­am­ine a per­son’s cur­rent level of in­come, or the ra­tio of per­son­al in­come to debt as a way to eval­u­ate a per­son’s cred­it­wor­thi­ness. That’s a strategy that Chi Chi Wu, a staff at­tor­ney at the Na­tion­al Con­sumer Law Cen­ter, also sup­ports. Cred­it scores should also take in­to ac­count the tough eco­nom­ic times in­di­vidu­als may face dur­ing a re­ces­sion, like un­em­ploy­ment or a tem­por­ary in­ab­il­ity to pay one’s bills, Wu says. “Cred­it scores should dis­tin­guish between people who are a hot mess versus those who have just fallen on hard times. Giv­ing them bad cred­it scores just keeps them down,” she adds.

Vant­ageScore does not in­cor­por­ate so­cial me­dia in­to its cred­it-scor­ing mod­els. In­stead, the com­pany leans heav­ily on the fol­low­ing ways to pre­dict someone’s cred­it score: The per­son’s abil­ity to pay bills on time, the his­tory and type of cred­it he uses, and his total cred­it-card bal­ances and total debts. A red flag pops up if someone ac­cu­mu­lates huge amounts of cred­it very fast.

In the latest ver­sion of its mod­el, Vant­ageScore no longer takes in­to con­sid­er­a­tion paid med­ic­al debt or oth­er types of paid debt that get kicked to a col­lec­tion agency. The com­pany no longer finds it “math­em­at­ic­ally sig­ni­fic­ant,” Burns says. Con­sumer ad­voc­ates, like Wu, ap­plaud them for ex­clud­ing this debt that can plague mil­lions of Amer­ic­ans and eas­ily drag down scores. The com­pany has also tried to take in­to ac­count the ef­fect of nat­ur­al dis­asters, like Hur­ricane Sandy, by pulling out the neg­at­ive con­sumer data caused by these pre­dic­a­ments. Burns likes to call these tweaks “nifty dif­fer­en­ti­at­ors.”

Right now, Vant­ageScore sells its cred­it-scor­ing mod­els back to the three ma­jor cred­it-re­port­ing bur­eaus. The long-term goal, however, is for Vant­age Score to be­come its own house­hold name, even if the fed­er­al gov­ern­ment’s ma­jor lenders, like Fan­nie Mae and Fred­die Mac, still do not ac­cept Vant­ageScore as a primary cred­it scorer.

Ad­voc­ates for first-time home­buy­ers and more di­verse pop­u­la­tions hope this will change and that a great­er share of lenders will be open to these dif­fer­ent al­gorithms to pre­dict cred­it scores. “We’re not look­ing for ways to get people in­to the sys­tem that are not qual­i­fied. We’re look­ing for oth­er met­rics to identi­fy people who will be suc­cess­ful,” says Gary Acosta, cofounder and CEO of the Na­tion­al As­so­ci­ation of His­pan­ic Real Es­tate Pro­fes­sion­als. “A large per­cent­age of first-time home­buy­ers or people from the His­pan­ic pop­u­la­tion have thin cred­it or very little tra­di­tion­al cred­it. But they have buy­ing power, job sta­bil­ity, and strong as­sets. The mar­ket­place even­tu­ally will be re­spons­ive.”

Cla­ri­fic­a­tion: This story has been up­dated to make it clear that Vant­ageScore only ex­cludes paid med­ic­al bills and oth­er types of paid col­lec­tion debt from the latest ver­sion of its scor­ing al­gorithm.

What We're Following See More »
In Dropout Speech, Santorum Endorses Rubio
1 days ago

As expected after earlier reports on Wednesday, Rick Santorum ended his presidential bid. But less expected: he threw his support to Marco Rubio. After noting he spoke with Rubio the day before for an hour, he said, “Someone who has a real understanding of the threat of ISIS, real understanding of the threat of fundamentalist Islam, and has experience, one of the things I wanted was someone who has experience in this area, and that’s why we decided to support Marco Rubio.” It doesn’t figure to help Rubio much in New Hampshire, but the Santorum nod could pay dividends down the road in southern states.

Rubio, Trump Question Obama’s Mosque Visit
1 days ago

President Obama’s decision to visit a mosque in Baltimore today was never going to be completely uncontroversial. And Donald Trump and Marco Rubio proved it. “Maybe he feels comfortable there,” Trump told interviewer Greta van Susteren on Fox News. “There are a lot of places he can go, and he chose a mosque.” And in New Hampshire, Rubio said of Obama, “Always pitting people against each other. Always. Look at today – he gave a speech at a mosque. Oh, you know, basically implying that America is discriminating against Muslims.”

Cruz Must Max Out on Evangelical Support through Early March
1 days ago

For Ted Cruz, a strong showing in New Hampshire would be nice, but not necessary. That’s because evangelical voters only make up 21% of the Granite State’s population. “But from the February 20 South Carolina primary through March 15, there are nine states (South Carolina, Alabama, Arkansas, Georgia, Oklahoma, Tennessee, Kentucky, Mississippi, and North Carolina) with an estimated white-Evangelical percentage of the GOP electorate over 60 percent, and another four (Texas, Kansas, Louisiana, and Missouri) that come in over 50 percent.” But after that, he better be in the catbird’s seat, because only four smaller states remain with evangelical voter majorities.

Rubio Now Winning the ‘Endorsement Primary’
1 days ago

Since his strong third-place finish in Iowa, Marco Rubio has won endorsement by two sitting senators and two congressmen, putting him in the lead for the first time of FiveThirtyEight‘s Endorsement Tracker. “Some politicians had put early support behind Jeb Bush — he had led [their] list since August — but since January the only new endorsement he has received was from former presidential candidate Sen. Lindsey Graham.” Meanwhile, the New York Times reports that fueled by resentment, “members of the Bush and Christie campaigns have communicated about their mutual desire to halt … Rubio’s rise in the polls.”

Sanders: Obama Is a Progressive
19 hours ago

“Do I think President Obama is a progressive? Yeah, I do,” said Bernie Sanders, in response to a direct question in tonight’s debate. “I think they’ve done a great job.” But Hillary Clinton wasn’t content to sit out the latest chapter in the great debate over the definition of progressivism. “In your definition, with you being the gatekeeper of progressivism, I don’t think anyone else fits that definition,” she told Sanders.