The Next Step in FICO Credit Modeling

Since its introduction by Fair, Isaac & Co. more than three decades ago, FICO has long been considered the No. 1 standalone credit decisioning model. Is there a way the banking industry can build on that foundation to create a more future-forward way of predicting lending outcomes?

The way the financial services industry analyzes data has evolved since FICO’s inception in 1989. New and exciting technology has led to innovative algorithms that give bankers a more defined look at an even greater data set. An all-encompassing view of a borrower’s story can bring a new realization: these new methods of analyzing credit, combined with the FICO mainstay, can lead to even better outcomes for everyone.  

Many facets make up an individual’s credit story — beyond payment history and amounts owed. There is data that, once analyzed, can give lenders critical insights into borrower characteristics that can’t be categorized by a single number. People are more dynamic than their credit scores.  

Imagine a traditional consumer credit scoring model as a printed picture: a one-dimensional take on a person’s whole life in credit. In that static picture, there are balances on debt obligations, utilization of revolving types of credit like credit cards, delinquency and statuses, among others. This information comes from the three major credit bureaus — Equifax, TransUnion and Experian — and represents a vast cross-section of loans originated by banks, credit unions, finance companies and other lenders across the credit industry. This information adds up to that single definitive score.

In contrast, non-traditional models that build on the foundation of FICO can incorporate additional predictive information. Think of it as the motion picture version that creates a more dynamic view of consumer creditworthiness. This model gives lenders an ability to assess point-in-time information and the momentum of trended credit data factors, which may help predict the future credit conditions for a potential borrower and allow a lender to make more informed decisions. Bankers have greater visibility into the depth of a borrower’s story, like balances or utilization increasing or decreasing, and can capture that relationship with risk outcomes.

Alternative data sources can complement static and trended credit history by introducing consumers’ checking history, property ownership and alternative finance activity into credit scoring models. Consumers with comparable credit files can have vastly different repayment history and patterns; incremental information related to creditworthiness equips lenders to optimize risk differentiation when the credit file alone doesn’t capture the full story.

Creating a new model to calculate and predict high-performing loans is no small feat. BHG Financial, a leader in unsecured business and personal loans and creator of one of the country’s largest community bank loan networks, once relied on the traditional credit scoring model to help with their decision-making. The company decided to evolve their credit model to identify miscategorized but high-quality borrowers that most lenders were missing.

BHG Financial data scientists partnered with TransUnion to analyze over 2 million consumer loans; each loan was over $20,000, had at least 36-month terms and originated between 2015 and 2017. This amounted to more than a billion pieces of data points to analyze and assess, resulting in their proprietary credit model, the rScore.  An updated credit model resulted in faster approvals, and the identification of subprime borrowers that perform well along with prime borrowers with high default rates.

Evolving the already successful and established FICO score, the chances are lower that good-paying borrowers will be labeled as high risk. This enables some lenders to approve pockets of creditworthy consumers that others might decline. At the same time, the chance of labeling risky borrowers as low risk also declines — allowing lenders to protect the credit quality of their portfolio.

Lenders unable to dedicate time and money to develop their own evolved credit scoring model can collaborate with companies that have created updated credit models, skipping the extensive research and the costly origination process. This gives them immediate access to purchasing top-quality loans with low risk, which can quickly strengthen their loan portfolio to meet their bank’s criteria. This solution is possibly the best answer to finding a more future-forward way of predicting lending outcomes.    

Completing the Credit Score Picture

Traditional credit scores may be a proven component of a bank’s lending operations, but the unprecedented nature of the coronavirus pandemic has their many shortcomings.

Credit scores, it turns out, aren’t very effective at reacting to historically unprecedented events. The Federal Reserve Bank of New York even went so far as to claim that credit scores may have actually gotten “less reliable” during the pandemic.

Evidence of this is perhaps best illustrated by the fact that Americans’ credit scores, for the most part,  improved during the pandemic. This should be good news for bankers looking to grow their lending portfolios. The challenge, however, is that the reasons driving this increases should merit more scrutiny if bankers are accurately evaluate borrowers to make more informed loan decisions in a post-pandemic economy.

For greater context, the consumers experiencing the greatest increases in credit score were those with the lowest credit scores — below 600 — prior to the pandemic. As credit card utilization dropped during the pandemic, so too did credit card debt loads for many consumers, bolstering their credit scores. In some instances, government-backed stimulus measures, including eviction and foreclosure moratoriums to student loan payment deferrals, have also helped boost scores. With many of these programs expiring or set to retire, some of the gains made in score are likely to be lost.

How can a bank loan officer accurately interpret a borrower’s credit score? Is this someone whose credit score benefitted from federal relief programs but may have struggled to pay rent or bills on time prior to the pandemic and may not once these program expire? Compared to a business owner whose income and ability to remain current on their bills was negatively affected during the pandemic, but was a safe credit risk before?

There are also an increasing number of factors and valuable data points that are simply excluded from traditional credit scores: rent rolls, utility bills and mobile phone payment data, which are all excellent indicators of a consumer’s likelihood to pay over time. And as more consumers utilize buy now, pay later (BNPL) programs instead of credit cards, that payment data too often falls outside of the scope of traditional credit scoring, yet can provide quantitative evidence of a borrower’s payment behavior and ability.

So should bankers abandon credit scores? Absolutely not; they are a historically proven, foundational resource for lenders. But increasingly, there is a need for bankers to augment the credit score and expand the scope of borrower data they can use to better evaluate the disjointed, inaccurate credit profiles for many borrowers today. Leveraging borrower-permissioned data — like rent payments, mobile phone payments, paycheck and income verification or bank statements —creates a more accurate, up-to-date picture of a borrower’s credit. Doing so can help banks more safely lend to all borrowers — especially to “near prime” borrowers — without taking undue risk. In many cases, the overlay of these additional data sources can even help move a “near prime” borrower into “prime” status.

While the pandemic’s impact will continue reverberating for some time, bankers looking to acquire new customers, protect existing customer relationships and grow their loan portfolios will need the right and complete information at their disposal in an increasingly complex lending environment. Institutions that expand their thinking beyond traditional credit scoring will be best positioned to effectively grow loans and relationships in a risk-responsible way.

Loan Growth: Curation, Credit Monitoring

SavvyMoney.pngOne community bank is using a fintech to deepen lending relationships with customers and help them monitor and improve their credit score.

Watford City, North Dakota-based First International Bank and Trust wanted to offer customers a way to proactively monitor their credit and receive monthly or incident-related alerts about any changes — without needing to use external vendors, granting external access to accounts or even paying for it. It chose to partner with SavvyMoney, which provides customers with their credit scores and reports alongside pre-qualified loan offers from within the bank’s online and mobile apps.

The fruits of the relationship were one reason the fintech was awarded the Best Solution for Loan Growth at Bank Director’s 2020 Best of FinXTech Award in May. CommonBond, a student loan refinancer, and Blend, which offers banks an online, white-label mortgage processing solution, were also finalists in the category.

In exploring how it could help customers improve their credit score and manage their finances, First International knew some customers were already using similar services through external websites. But the $3.6 billion bank wanted to convey that it had invested time and IT resources to ensure SavvyMoney’s validity, accuracy and status as a trusted partner, says Melissa Frohlich, digital banking manager. The SavvyMoney feature takes about 45 seconds to activate once a customer is logged in, and the customer experience is the same in the mobile app or website.

“From the fraud standpoint, we definitely recommend to our customers that … they use SavvyMoney because it’s free to them,” Frohlich says. “Especially with all the breaches that happen, it’s a good way for them to self-monitor their credit.”

The bank also uses the platform to share specialized credit offers along with a customers’ loan information and credit score, which it crafts using public records and extends based on internal criteria. It has launched two credit card balance transfer offers since rolling out the product two years ago. The fintech offers First International a way to “slice and dice” data to truly target customers with customized offers, as opposed to “throwing out a fishing line and hoping someone bites,” she says.

Launching the offers takes “very little” time to implement and consists of updating a term sheet, whipping up bank graphics and sending out a simple email blast. The first offer netted more than $190,000 in balance transfers — all from one email campaign.

“It was just very, very little work for us with pretty significant impact, without a ton of manpower or money that we had to put into it,” Frohlich says.

The balance transfer offer included messaging about how much customers would save with the new interest rate. If First International wanted to offer auto loan refinancing, it could input different rates based on the year of the vehicle and loan term.

First International was drawn to SavvyMoney in part because it had an existing relationship with a variety of core providers. That’s key, given that SavvyMoney connects to a bank’s core to pull in personal customer information from online and mobile banking sources. And because it would be sharing customer data, First International spent several months conducting due diligence, combing through SavvyMoney’s system and organization controlsreports and speaking with both its core and the fintech.

Frohlich says the actual implementation took about a month and was as straightforward as flipping a switch to activate the capability in customer accounts. She continues to work with her representative at SavvyMoney to add or change loan offers.

“They have probably the best integration that I’ve seen with Fiserv from a third party or a fintech, out of any other product that Fiserv doesn’t own,” she says. “The actual implementation was the best that I’ve ever taken part in.”

SavvyMoney can also integrate with the bank’s new loan platform that was slated for a March launch, a fact that Frohlich didn’t know when the bank selected either. Loan applications submitted through SavvyMoney will feed into the software’ auto decision-making.

“That will be a game changer for us, then we will heavily start doing more promotions,” she says.

Even after the bank switched cores, it has been able to keep SavvyMoney given its vendor relationships with other cores. “There have been other solutions, that now that we’re moving to a different platform, that I could consider,” Frohlich says. “But to be honest, our experience has been so great with SavvyMoney that I have no reason to look elsewhere.”

Nine Strategic Areas Critical to Your Bank’s Future

strategy-6-30-17.pngHow should banks determine the best way to proceed over the upcoming quarters? While no one can predict the future, there are several critical developments that anyone can keep an eye on. These are the areas that are most impactful to banks and for which they need to strategize and position themselves.

Rising Rates: Obviously, rates are rising but by how much? Banks should position for moderate hikes and a slower pace of hikes than the Fed predicts. The Fed predictions on rate hikes have been overstated for several years running. The yield curve for the 10-year Treasury is flattening as of late, which also indicates fewer hikes are needed. A reduced duration for assets and reduced call risk makes the most sense; but practice moderation and don’t overdo it. Too many banks had their net interest margin crushed by being too asset sensitive and waiting for rates to increase while we had eight years of low rates. Check your bond portfolio against a well-defined national peer group of banks with similar growth rates, loan deposit rates and liquidity needs. Very few banks perform this comparison. They just use uniform bank performance reports or a local peer group. Every basis point matters, and there is no reason to not be a top quartile performer.

Deposits: Buy and/or gather core deposits now. Branches provide the best value. Most banks overestimate what deposits are core deposits, meaning they won’t leave your bank when rates rise. Like capital, gathering core deposits is best done when it is least needed.

Mergers and Acquisitions: If you are planning on selling in the next three years, sell right now, as optimism and confidence are at 10-year highs. If you are a long-term player, go buy core deposits, as they are historically cheap and you are going to need them. They are worth more now than perhaps ever before.

Get Capital While You Still Can: Solve your capital issues now. Investors are probably overconfident, but banks have done well the last seven years and finally, they aren’t taboo anymore. Investors want to invest in banks. That always happens before something bad in the economy occurs, so get it while you can.

Real Estate Carries Risk: With regulators mindful of capital exposure and real estate deal availability being spotty, it’s best that banks be wary of deals in this area. Commercial real estate linked to retail is more and more being viewed as extremely risky. There is an all-out war being waged on store retailers by online retailers. Since retail is a huge sector of the U.S. economy, investment will follow the online trend. Industrial real estate has become “retail extended” with the least amount of real estate risk.

Beware of Relying on Credit Scores: Banks need to be careful of the credit cycle. Consumers are loaded full of debt. Cars and homes are too expensive relative to wages and affordability. Credit scores probably don’t capture the downside risk to the consumer.

Get Ahead of Your Risks: Cyber-risk is a major and very real risk. Get ahead of the curve. Two other areas bearing risk are 401(k) plans and wealth management areas as they are especially exposed to litigation and are a nightmarish mess to be addressed. 401(k)s are overloaded with too many choices, fiduciary risk, performance issues, excessive fees and conflicts of interest. Get help now or you may be painfully surprised.

Marketing: Your bank had better get creative with digital marketing opportunities for your website as well as mobile devices. Why? Billions are being invested into financial technology companies and it’s easier for fintech to learn about banking than it is for bankers to learn about fintech.

Millennials: Surveys from The Intelligence Group and others show that finding young, motivated workers, and then retaining them, may be a challenge.

  • 45 percent of millennials believe a decent paying job is a right, not a privilege.
  • 64 percent would rather make $40,000 at a job they love versus $100,000 at a boring job.
  • 71 percent don’t obey social media work policies.
  • Millennials are proving to be more loyal to employers than previous generations, and are better at multi-tasking than previous generations.

Hopefully, some of these items provide bankers strategic ideas to incorporate over the next two or three years.

Now is the time to chart your course.

Is This the End of the Road for Credit Scores?

4-8-13_Sutherland.pngFast Fact: PayPal’s mobile payment processing jumped from $141 million in 2009 to $4 billion in 2011 and is estimated to more than double in 2012. In just over two years, Square has more than 2 million merchant customers—25 percent of the U.S. merchant population.

Some of the holiest tenets of consumer banking are being questioned. Newer players with a totally different attitude toward their customers who understand technology and the Internet are winning market share and earning customer loyalty. 

In the context of financial transactions, the credit score is to individual fitness what the heart is to physical wellbeing. This has been the be-all-end-all metric that determined consumer lending for over half a century and has powered many a consumer revolution in loans, cards or mortgages.

However, the logic and algorithm of the credit score were developed before the age of connectivity, databases, analytics and big data. And although the credit score has transformed itself over time by improvising for various asset classes, it has not truly leveraged big data to assess individual financial potential as opposed to actual performance.  Are we therefore now beginning to see the end of the credit score as we all know it?  

With the growth of digital wallets, mobile payments and the generational shift away from paper checks and brick-and-mortar bank branches, is it time for a new credit score or new metric to enable the next revolution in lending? Or will current providers embrace a “different strokes for different folks” attitude as the millennial generation overtakes the baby boomers as the single largest customer segment for a banks’s services and products? 

Fast Fact: Annual check usage in the U.S. has dropped from 16.9 billion in 2010 to 5.1 billion in 2012. Average customer visits per branch per year have dropped from 21.3 in 1995 to 3.2 in 2012.

The growing volume of payments with social dollars versus physical currency could signal an opportune time to revamp the underlying credit score algorithm and logic or even adopt a totally different approach. Consider, for example, the growing reluctance of the 19- to 30-year age group to open a bank account or write a check. Unlike other generations, they now have choices and providers to enable a variety of financial transactions. 

Also, the not-so-palatable fact is that this new generation of transactions is faster, safer, more convenient and less costly—four dangerously compelling reasons for retail banks to revisit and realign the prevailing offerings. 

Consider the success of the prepaid card as the emerging alternative to the bank account and the resurging demand for payday loans as the preferred financing medium. We are already seeing startup banks promote alternative scores such as the CRED from Movenbank, which uses social media status as the leading input into this very interesting, real-time metric. Will we see Facebook, Google and Apple providing input to credit bureaus to complete the social aspects of a consumer’s credit profile?

Fast Fact: Prepaid debit card payment volumes have grown from $202 billion in 2011 to $297 billion in 2012.

In the past, the terms “unbanked” and “un-bankable” were virtually synonymous and represented a huge market. That, however, is no longer true. In fact, today’s “unbanked” provide a better business opportunity compared to the “banked.” It is therefore essential that we need to evolve new metrics to supplement the credit score as we know it today. A recent Sallie Mae and Ipsos survey found that the percentage of undergrad students who own a credit card was down from 49 percent in 2010 to 39 percent in 2012—a further indication of the lack of desire among the millennial consumers to have any credit history. That might be a good thing in some ways, given the state of the economy and the need to rein in consumer spending. But it might not be a good thing for the economy, as the supply chain cuts production even before we know it and has a head-on impact on the entire value chain.  

This notion of “credit-less” consumer s raises a number of questions:  Will large institutions like Citigroup, Bank of America and JPMorgan Chase & Co. choose to evolve their own internal metric to score a consumer rather than relying on the credit bureaus? Interestingly, in developing countries where there are no credit bureaus, that is exactly the case. Banks have their own surrogate credit scores and this approach seems to be working well in those markets. 

But will Starbucks, which makes more than 30 percent of its daily store sales on a mobile wallet, be reporting to credit bureaus soon? Or will Amazon, mobile wallet company Isis or Google do so?  More to the point… should they? Or instead should they embrace big data analytics and be their own card issuer because they already have daily data on a customer’s behavior? And if that’s the case, will it impact a customer’s credit score or his financial health if he switches from a $4.50 latte three times a day to a $1.80 coffee daily? 

Are we headed for a new world where a micro finance credit bureau will emerge and manage all interactions of less than $500? With the convergence of telecom, tech, banking and retail industries during the next few years, it will be interesting to see the demise of the credit score as we know it and the growth of a new medium of rating consumer credit. As it is, ask the folks from Canada, the United Kingdom or Asia who relocate to the United States with large bank balances (and, in some cases, Swiss bank accounts) yet are unable to get a mortgage or credit card and end up purchasing everything with cash. Even in the traditional sense, we have quite a way to go before the credit bureau is able to do the greatest good for the greatest number.