Traditional credit scoring is an outdated method that is holding back the economy. This is particularly so for lenders in underbanked regions and those appealing to younger generations. Millennials distrust big banks and increasingly turn away from credit card offers, which means credit card data is less relevant than ever. Meanwhile, there is a growing number of unbanked individuals seeking access to financial services, particularly women in rural areas.

All of this is in the context of the microfinancing industry being valued at $178.84 billion in 2020 and projected to reach $496.90 billion by 2030. Online lenders must find new ways to spot default and fraud risk if they are to capture this growth. 

loan portfolios in different countries

What Is Alternative Credit Scoring?

Alternative credit scoring collates reliable data across a number of points to determine whether the applicant has the means and the intention to repay the loan. 

A customer’s online presence, otherwise known as their digital footprint, can be a powerful form of alternative data for credit scoring models. A digital footprint proves that the person does exist and is probably legitimate; additional data points reveal some information about their financial stability. Conversely, a fraudster, would likely use a throwaway address or a burner number, and not have a digital presence. 

For example, a LinkedIn account (and the details within it) suggests the applicant is a real person who is also in regular employment. Employment data can also be combined with sector data, allowing the lender to guess the income level of the debtor and make a suitable loan offer to them.

Other online data points reflect a level of ‘lending trust’. For example, if a customer is regularly paying their bills to a number of online accounts, such as Netflix and Amazon Prime, it suggests they also have the finances to make small loan repayments. 

Digital footprints come most handy in markets where traditional bureau data is unavailable, other data sources are stale or inaccurate, or the target group is simply underbanked. All these situations make it difficult for lending organizations to meaningfully assess risk.

Assessing Credit Worthiness With Alternative Data

See how to leverage digital footprinting to gain a comprehensive view of financial reliability to enhance decision-making.

Read More

How Does Alternative Credit Scoring Work with Social Profiling?

Lending is all about trust. The problem is finding the right signals about a given customer that allow you to determine (or deny) that trust. Social and digital signals are a great way to do that. 

Depending on the user’s country, you can reasonably expect that good debtors and bad debtors will have a different mix of online sites and services for which they are signed up. 

For example, a fresh user who doesn’t have an account with their country’s largest messaging platforms could indicate a bad-faith actor, who you can block or ask for further documentation – such as income statements.

On the other hand, someone who has active GitHub, LinkedIn and Skype accounts is more likely to be trustworthy. 
Such an approach can augment your credit scoring models in a way that allows you to take on customers who would otherwise look too risky because of their underbanked nature. Moreover, it also lets you screen out malicious actors even before they reach the stage of mandatory KYC verification.

How to Collect Alternative Data for Credit Scoring

In addition to profiling a customer’s social accounts, there are more ways data can be used to access creditworthiness. Internet usage is increasing all over the world, even in underbanked markets, which makes online activity a treasure trove of customer insights.  

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 website contains a lot of digital information. Using private mode or an emulator increases the likelihood that they are not who they claim to be.
  • Email profiling: A reverse email lookup will tell you if the customer’s email address doesn’t exist, or is from a suspicious or disposable domain – both of which mean it is also unlikely they are trustworthy. 
  • Phone analysis: Phone numbers leave a breadcrumb trail of evidence. The use of cheaper mobile carriers in some regions can indicate lower financial stability while fake phone numbers suggest fraud.
  • Location: Spotting applications from high-risk locations helps you filter out customers with a high likelihood of defaulting, as well as areas high in rife with fraud.
data points aggregating during digital fingerprinting as an alternative credit scoring method

Digital Lending and Risk

One consequence of the increase in smaller, frictionless lending is that it puts lenders at risk. While it means legitimate borrowers can create new accounts and access their money quickly, it also opens the door to those likely to default on loan repayments. 

Defaulters are increasingly targeting microloan offers, using a combination of known attacks and techniques. This is something lenders must get control of because every fraudulent dollar in a digital loan costs the lender $2.82, much higher than other industries including ecommerce, retail and financial service.

Fraud Risk For Online Lenders

  • Identity theft: Opening a new account with stolen credentials without any intention of repaying the debt.
  • Going AWOL: Opening an account quickly, borrowing funds, and vanishing.
  • Account takeover fraud: Phishing for current account holder information and exploiting it to borrow money for themselves.
  • Synthetic identities: Combining the personal information of real people into new synthetic IDs then taking out a large loan and disappearing. According to the US Federal Trade Commission, synthetic ID fraud is the fastest-growing form of identity theft.

Fraudsters Know How to Cheat Most Background Checks

Fraudsters are smart enough to test their stolen or synthetic data through their own online background check systems before using it in the real world. 

Once they know the credit score of the person they are pretending to be, they can apply for a loan with a higher success rate than the average borrower.

In some cases, fraudsters even acquire the assessment criteria from background check companies, and simply manufacture the right user profile to meet the criteria.

Key Takeaways of Alternative Credit Scoring

Building a solid and efficient online credit scoring model in the digital era is challenging, yet entirely possible. The good news is that customers’ digital footprint is increasingly large and available to aggregate with the right tools. Using SEON’s end-to-end fraud and default prevention solution, you can lower default in underbanked demographics without closing the door to valuable customers.

Our default prevention software is powered by machine learning, meaning it adapts to changing customer default trends. Our custom risk rules also mean you can create a risk-scoring model that flexes to both these trends and your changing risk appetite. You can then apply this risk score to your existing model to improve accuracy and reliability.

Not only can you reach more of the right customers, you can understand how much they should borrow, how fast they can pay back the funds, and whether they should be granted access to your products – all helping you grow your business safely.

Share on social media

Sign up to download

In order to download this PDF, please complete the form.

Thanks for submitting the form, click the button below to download our guide.

Click the button below to download our guide.

download box icon