Posted on September 19, 2019


The number that strikes fear in the heart of today’s consumer isn’t their age or their weight, it’s their credit score. We know that our credit scores are important for a wide variety of services from securing loans to making us a competitive candidate for renting an apartment. Even for a seasoned borrower, taking out a loan is a nerve-wracking and frustrating process. We sit on pins and needles to find out if we are approved for our loan and if our rate will be competitive.

However, both lenders and borrowers are realizing that the current process needs a makeover. Consumers are frustrated with current credit models and are tired of the long process of jumping through hoops to obtain a loan. New borrowers have to plan well before even applying for a loan, so that they can build up their credit, possibly even opening credit cards that they don’t really need. Finally, lenders are frustrated with missing out on a market of potential new customers that they can’t service due to low or no credit score history.

Borrowers are fed up with current credit models and loan application processes… and lenders are noticing and adapting. Lenders are revolutionizing how lending data is viewed and are thinking about new credit models through a modern approach.


There are several credit score models available, but over 90% of lenders use the FICO score as a standard. Five elements make up a consumer’s credit score, and savvy consumers know how to make the formula work for them. The five elements of a FICO credit score are:

  • Payment History (35%)
  • Credit Utilization Ratio (30%)
  • Length of Credit History (15%)
  • New Credit (10%)
  • Credit Mix (10%)

Although predictive credit scores like the FICO score have been helpful for lenders to assess the creditworthiness of a potential borrower, the way we use credit as a society, as well as our attitude towards how we shop, is influencing the next generation of credit models.


The last major shakeup of the credit industry was in 1989 with the introduction of the FICO credit score. Since that time, the way we use credit has changed, but the credit score formulas have evolved at a slower pace. Consumers are using more credit than ever before and at a younger age than previous generations. Lenders are taking notice that new generations of borrowers are using credit for everything from student loans to medical bills to even a one-dollar swipe from a vending machine for a snack.

When it comes to applying for credit, modern consumers want a transparent credit scoring system with a simple and convenient application process (preferably online or via an app) and don’t want to speak or meet with someone in person. They want fast decisions regarding credit approval and when comes to actually receiving their loan, they want same-day access to their cash or credit.



Although the implementation of new credit score models by lenders might seem to move at a glacial pace, it’s still progressing. Traditional credit scoring companies like VantageScore and FICO are already adapting their traditional credit scoring models to better reflect how modern consumers are using credit.

For example, revised credit scoring models treat medical and non-medical debt differently. The medical billing process is complicated and it can take months if not years for patients and insurance companies to work through billing disputes. Lenders are finally recognizing that medical-related debt is not a hugely significant predictive factor in whether or not borrowers will default on a loan.


New alternative models are using Machine Learning, a subset of AI technologies and Big Data, to give lenders not only a new method to score consumer credit, but they are working towards predicting a consumer’s future credit score. Current credit scoring models act as a snapshot in time and are reactive to a consumer’s actions. New models are looking at using big data to trend a customer’s future creditworthiness.

Lenders are looking at consumer data that is already available to help them to predict the likelihood of borrower payback rates, especially for borrowers who have a limited credit history. Payment history from services that consumers use every day such as utility or cell phone bills (with customer permission) has been shown to have a strong correlation with installment loan repayment rates. By using more data points in a credit model, lenders are able to identify patterns and predictive behaviors.

In addition, service providers are experimenting with using existing customer approved data to give both their customers and lenders instant and predictive small business credit scores. Services like Intuit’s QuickBooks are supplying lenders with existing customer cloud-based data to simplify and speed up the underwriting process for small-business loans.


Some lenders are experimenting with credit models that use data points that are outside of traditional sources. Experimental credit models are evaluating how clickstream data or the clicks and activity from a customer’s usage of their website can predict customer credit behavior. Likewise, experts are researching how other experimental data sources like address history, bill payment methods and, even social media activity can be used to add additional key indicators of a consumer’s creditworthiness.


As the modern consumer’s use of credit and purchasing behaviors continue to evolve, credit scoring models will continue to evolve as well. With the help of Big Data, Machine Learning and, additional data points, lenders are trying to keep up with changing consumer needs while also protecting themselves. Although the future of credit is becoming a more agile process, lenders will still need to make sure they are protecting their own interests as well as respecting the progress that has been made in equal lending opportunities.