You Are More Than Your Credit Score

If you are planning to borrow money any time soon, it is likely you will be judged by a three-digit number known as your credit score. Fair, Isaac and Company – FICO — was the analytics company that pioneered the concept of credit scoring now used by lenders around the world. Since then, other companies have joined in with their own credit scoring models.

The friendly credit scoring folks boil your credit history down to a three-digit number reflecting several key factors that help determine the creditworthiness of an individual. These include your payment history, how long you’ve had credit, the types of credit you’ve had, how much you owe versus how much you have borrowed and how often you apply for credit. These factors combined produce your credit score, which is a key part in a lender’s decision as to whether you are creditworthy, and if so, what loan terms you should be offered.

Although this number and related methods have served the lending community well over the years, in order to better serve future borrowers, the next generation of lenders must factor in a richer, more complete set of data, one that not only looks at the individual behind the loan application but also the people – the “social network” – around them. Bringing the community into lending provides a more complete representation of a person’s creditworthiness, leading to more accurate rates and, ultimately, money saved for borrowers.

An Incomplete Reflection

The FICO score and other analytic models have been remarkably useful since their creation in the late ‘80s, but as with any established process, there are limitations.

Today’s algorithms are, no doubt, impressive. In less than a millisecond, they can parse vast mountains of data to make more informed decisions, examining many of the key factors traditionally used in determining a borrower’s likelihood of repayment. With power like this, it’s easy to assume every base is covered – but is that really the case?

One mistake can deny a good borrower access to credit, and at a minimum diminish their ability to secure a great rate. For example, many Americans with excellent credit scores – in this example, about a 780 FICO score — can lose up to 100 points off their credit score for a single 30-day late payment. What’s more, getting a credit score “back on track” can take upwards of two to three years.

As we all know, there’s more to a person than just their past – and there’s more to someone’s creditworthiness than their individual financial circumstances.

Are you working toward a career in medicine, or perhaps as a computer programmer? Do you have one semester left before earning an MBA? Do you come from a close-knit community that is committed to helping you succeed? An algorithm won’t account for these factors when it determines your loan eligibility or APR. Its focus is narrowed only to past borrower performance history, in isolation.

Friends and family have the best insight into a borrower’s potential and can serve as a check-and-balance when paired with data-driven methods for evaluating creditworthiness. Reliance on data science and objectivity should still underlie loan applicant evaluations, but when we consider individual potential and social factors coupled with data-driven analytics, a more complete, truthful assessment of an individual emerges.

Loan Decisioning 2.0

It’s safe to assume people understand people better than machines ever will.

Before score-based loan decisioning, real people decided who got approved for a loan. Lenders consulted friends, family, neighbors and employers to get a sense of your creditworthiness. Modern data infrastructures did not exist, so it was a borrower’s network that factored heavily into a lending decision. Lending was communal. It was human.

As the financial industry recovers from the wounds of the Great Recession, we are afforded the opportunity to rethink lending – a “Loan Decisioning 2.0” – but if we are ever going to create such a change, in addition to data we must again factor for a human perspective. The intention is not to replace the current system, rather to complement those data-driven decisions with real-life network data. Together, they will ensure a clearer reflection of an individual borrower.

Let’s take the best of lending’s roots, in an objective and fair manner, and ensure borrowers are afforded manageable interest rates that reflect their true potential. Let’s consider the people who know them best when making a decision.

Let’s put the social back into lending.

This story is an Op/Ed contribution to Credit.com and does not necessarily represent the views of the company or its partners.