Lenders wrestle with the nuances of modern credit score pricing

Mortgage lenders are currently wrestling with a high-stakes puzzle: how to accurately compare the new credit score models hitting the market. The differences are significant and carry major implications for risk assessment, loan pricing and secondary market returns.

In late April, the Federal Housing Finance Agency (FHFA) rolled out a program allowing the exclusive use of VantageScore 4.0 for loans delivered by a group of lenders to the government-sponsored enterprises (GSEs) Fannie Mae and Freddie Mac. The future use of FICO 10T will also act as an alternative to the long-standing FICO Classic.

Not to be left behind, U.S. Department of Housing and Urban Development (HUD) Secretary Scott Turner signaled that Federal Housing Administration (FHA) loans will also adopt these alternatives in the coming months.

For now, lenders participating in the FHFA’s rollout program have a temporary workaround. They’re applying a 20-point cut from FICO to VantageScore to figure out where a loan should be priced in the grid.

While United Wholesale Mortgage (UWM) publicly announced this strategy, sources tell HousingWire it’s actually the practice among other participating lenders. These lenders are also relying on multiple models to double-check accuracy and minimize risk.

Guild Mortgage has already started to compare how the same loan scores across all three models, but it’s in the “very early stages of collecting this data,” according to David Battany, the company’s executive vice president for capital markets.

“When you see a delta between two models of 40 or 80 points, that’s pretty significant,” Battany said this week during a session on the new credit score models at the Mortgage Bankers Association (MBA)’s Secondary and Capital Markets Conference in New York. “When you think of Classic FICO, every 40 points of score equals a doubling of default rate.”

But default risk isn’t the only curveball secondary market investors need to model. Economists warn that these new scores could trigger other unintended consequences.

“For us, the prepaid risk is that you have a low FICO borrower, and he scores higher on Vantage, because most Vantage scores are a little bit higher,” Jeana Curro, managing director and head of agency MBS research at Bank of America, said during a session on general market trends. “That creates a refi opportunity that you know would not be foreseen, would not be estimated by models.”

Curro stressed that the industry still has a “way to go” with implementation, as not everyone is fully prepared. In her opinion, nonbanks are driving the conversation, while traditional banks are being left behind.

Tricky calibration

FICO and VantageScore themselves warned about the nuances between their models and the potential headaches of calibration.

“I wouldn’t underscore it and make it sound too easy to do the calibration,” said Ethan Dornhelm, head of scores analytics at FICO. “Certainly, calibrations are possible, but we do see that there can be drift over time, and given that the two algorithms that are the modernized credit scores are different, they could drift slightly differently. So, it will be a case of not just calibrating one time and being done with it, but rather careful and close monitoring over time.”

VantageScore recommends probability-of-default mapping, saying that translation tables are straightforward.

“What we recommend doing is to basing it on the probability default, so you have the similar expected outcomes when you’re looking at converting the scores, and we’re about to provide some more data on that,” said Rikard Bandebo, chief strategy officer and chief economist at VantageScore.

Most lender systems are built around a single credit-score field. Adding a second introduces major operational and policy questions. A concern is with cherry-picking, since lenders might simply submit whichever score makes the loan look more affordable for the borrower and ignore the actual probability of default.

“With regards to gaming, there have been studies not commissioned by either FICO or Vantage that have expressed concerns that at a given score band, defaults may increase by as much as 30% if gaming runs completely amok, and we just don’t know at this point what the dynamics are going to look like in this two-score lender choice setting, as far as how much gaming actually occurs,” Dornhelm said.

VantageScore downplayed these fears. Bandebo acknowledged that while the potential for gaming warrants study, research from Prosperity Now indicates that “it’s actually not going to increase the risk any more than the current system.”

Secondary market jitters

Lender adoption is only chapter one. The broader mortgage ecosystem — comprising warehouse lenders, secondary investors and other key players — has largely been in a “wait-and-see” holding pattern, sources say.

In late April, Newrez originated $10 million in mortgages scored with VantageScore 4.0, which were then securitized by Freddie Mac. This pilot effectively helped federal housing agencies greenlight the broader use of modern credit scores.

Bob Johnson, head of originations at Newrez, explained that Freddie Mac approached the company to see if it could “test the plumbing.” Newrez was “able to make those deliveries and fully test out the system,” he said.

But the secondary market was not fully tested, sources said. The first multilender GSE securitization containing VantageScore-underwritten loans totaled just under $8 million within an $11 billion pool, according to Dornhelm. He added that FICO reported one single-lender securitization under FICO 10T, with more expected in the home equity line of credit (HELOC) space later this year.

VantageScore counters by pointing to its proven track record outside the mortgage realm. The model already drives roughly 10% of asset-backed securities (ABS) issuance — including credit cards and personal loans — through major issuers like Synchrony and Toyota. Bandebo added that ratings agencies are ready and view the transition as manageable.

Different models, some similarities

The new score models are similar to Classic FICO because they all predict the likelihood of default over a two-year horizon, use the 300-850 score range, and incorporate utility and telecom data when available.

What makes them different is that both FICO 10T and VantageScore 4.0 use time-series balance, payment and utilization data rather than a single point-in-time snapshot. Both new scores factor in rental payment history — although less than 5% of files currently contain it, which represents a major growth area for financial inclusion. They are also built on more recent data and better reflect modern consumer behaviors.

But points of contention remain. While FICO 10T builds bespoke models for each bureau, saying that it maximized their unique data, VantageScore 4.0 uses one algorithm across all three bureaus for score consistency.