Exploring the benefits of a credit scoring model with alternative sources instead of credit bureau data.
As long as there has been money, there have been systems for loaning it. And as the way we process transactions and payments change, so should the way we assess risk or underwriting.
The fact, however, is that loan companies are a high target for fraud, especially in the digital era. Every dollar lost by digital lenders ends up costing them a whopping $2.82 – a much more damaging cost than in ecommerce, retail or other fintech industries.
This article will look at why traditional credit scoring fails online, and how to patch the holes of missing data, whether you are offering micro loans or more standard ones as part of a banking institution.
The Traditional Credit Scoring Model
Credit scoring is a form of risk assessment performed by credit bureaus. That is to say: how likely is the borrower to pay back the loan? Historically, the data used to answer that question included:
- Income statements
- Spending habits
- Debt history
- Card usage
Credit scoring bureaus cover various regions across the world. For instance, you have FICO in the U.S. and other parts of the world, and Equifax in the UK. They have different methods to collect the data, but the goal is the same: to create a model that can predict how safe it is to lend to a borrower.
However, in the digital era, we find these methods can come short, or worse, be fooled by fraudsters. Here’s why:
Why Credit Scoring Comes Short – False or Stolen Data
The first problem traditional credit bureaus face is that data can be falsified or stolen. We are talking about two clear forms of fraud, namely identity fraud and synthetic ID fraud.
According to the U.S: Federal Trade Commission, the latter is the fastest growing form of identity theft. It happens when criminals steal part of someone’s real ID (name, social security number or bank account) and combine it with fictional data.
So how do fraudsters acquire data that helps fool credit scoring bureaus? One method is to use stolen data from children or teenagers who have a clean transaction history. This goes to show that fraudsters will stop at nothing to be able to borrow money from loan companies without the right security in place.
Running Their Own Background Checks
In fact, fraudsters are smart enough to test their data through their own background check systems. Since there are paid services that let you perform credit checks online, the fraudsters can simply build their application file, use a stolen credit card, and purchase the service. Once they know their credit score will be high, they can apply for a loan with a higher success rate than for the average borrower.
In some cases, fraudsters even acquire the questions from background check companies, and simply manufacture the right user profile to meet all the right criteria.
When the Credit Data Simply Isn’t There
In spite of an increase in financial inclusion around the world, there are still around 1.7B adults who do not have access to financial services.
The unbanked, however, aren’t only found in developing countries, as they count anyone who relies on a cash economy for a variety of reasons:
- Inability to afford banking fees
- Lack of trust in financial institutions
- Reliant on a family member’s account
- Inability to produce the right documentation
In fact, 25% of US households are either unbanked or underbanked (when they do not have enough money to keep an account opened).
Sourcing Alternative Data For Credit Scoring
Enter digital footprint analysis. In a nutshell, it’s about using information from someone’s Internet usage to get a sense of who they are. And the reason it’s a treasure trove of data is that digital usage is increasing all over the world, even in markets with high percentage of unbanked citizens.
Here are examples of the kind of data you can get, simply by enriching your basic KYC info:
- Device fingerprinting: the phone, computer or tablet that borrowers use to connect to the lending platform contains tons of info. Are they using private mode or an emulator? This could increase suspicion that they are not who they claim to be.
- Email profiling: does the email address exist? Is it from a suspicious, disposable domain? Or one that doesn’t require any verification during sign up?
- Phone analysis: are they signing up with a real phone number? From a fixed line or mobile? And did they use that number for messaging services?
- IP analysis: one of the oldest and easiest forms of security available: looking at the origin of the connection. Is it from the right location? Or likely to be masked via TOR or a VPN?
While these extra data points might seem unrelated to credit scoring, they are actually a fantastic way to create a very real user profile. To learn more about the process itself, check out our infographics about credit scoring.
In fact, a leading micro lending company in Asia used our phone and email profiling tools to link users with social media profiles. They found that 75% of defaulting customers had no social media presence – a powerful predictor of which customers to flag in the future.
Digital Footprint for Credit Scoring – Key Takeaways
Building a solid, efficient credit scoring model in the digital era is challenging, yet entirely possible. The challenging part is about trusting the information you will acquire through standard KYC processes. It’s also about avoiding fraud from stolen identities and synthetic identities.
The easy part is that users’ digital footprint is increasingly large, and available to aggregate with the right tools. Using a phone, email or social media profiling solution, you should have no problem enriching data from users who are considered unbanked, or to confirm their identity.
Once you know they are who they claim to be, it will be easier to understand if they can access loans, how much they could borrow, and how fast they can pay them back to ensure your loaning business can grow safely.