How data is helping B2B fintech lenders step up to address loan application fraud
- Alternative data leads to predictive models for fintechs -- risk modeling, fraud detection, and lead scoring.
- In the third part of this article series, we discuss how alternative data is a solution against loan application fraud.

In the first article of this series, we asked you how you use external or alternative data. After receiving the results from the survey questions, it is evident that external data is increasingly important. 90% of the respondents indicated that external data was valuable, but only 9% stated that they had a strategy to access and use external data. Modern data architectures need to evolve to better incorporate relevant external data signals into data pipelines.
In both the first and second articles, we discussed how external data could help fintechs with use cases such as B2B loan default risk mitigation and B2B lead enrichment and scoring. This third and final article will discuss preventing the risk of fraud in loan applications with external data.
How alternative data helps
SMBs are increasingly turning to fintechs to provide more agile loan approvals with less stringent background checks than regular banks. This is fintech's great advantage over traditional financial institutions, but it comes with the added tendency to attract high-risk borrowers. For fintechs, 6% of loans are made to fraudulent business borrowers.
When it comes to processing SMB loan applications, it's essential to know if they will be able to tell if the applicants are who they say they are and can cover the loan payments. Alternative data can help create better predictive models in three key areas for fintechs: risk modeling, fraud detection, and lead scoring.
If you're in the fintech space, especially if servicing SMBs, Tearsheet would like to learn more about your relationship with data in the survey below.
Survey: How do you use external (alternative) data?
Risk modeling
Periodically, major global, local, or industry-specific events occur, throwing risk models into disarray. The mass shutdowns of businesses and stay-at-home orders caused risk models to break down over the last two years.
Lenders need to find new ways to measure their borrowers' default risks, as their current methods, relying on historical, internal data, are ineffective.
By enriching internal data, organizations can better assess lending risk to applicants. Lenders need to correctly avoid high-risk applicants and identify quality applicants and not falsely disqualify them.
Examples of external data include:
- Financial activity such as income, borrowing, payment history, assets, and liabilities
- Company data that includes years in operation, company type, and search trends
- Web presence data, such as the domain creation date, domain expiry date, number of related links, and website global traffic rank
- Company credit history
- Internet and social media data
By employing these types of external data signals, organizations can retrain existing risk models with new datasets and reduce their default rate by 10%.
Fraud detection
Lenders also have to deal with fraudulent loan applications. PwC's Global Crime and Fraud Survey found that nearly half of all businesses had experienced fraud in the previous two years, with an accumulated cost of $42 billion.
The online application process is remote, and decisions are made quickly compared to banks. Several online lenders don't do thorough background checks, and rely on basic information to make lending decisions.
Obtaining alternative risk scores based on various economic and financial health data can help indicate fraud risk.
A few examples of the types of alternative data that can help to improve loan application fraud models are:
- Web presence data, providing information on an applicant's website such as its global traffic ranking, and number of related links.
- Owner related data, such as a phone validation score
- Web data indicating whether the applicant's website has e-commerce functionality or is linked to services such as PayPal.
A more nuanced predictive model can take into account online evidence of past fraud by incorporating information from multiple regions, sources, and past vendor relationships to assess the validity of the applicant's identity.
With more accurate fraud detection models, we see online lenders boost their fraud detection rate by up to 92% on applications before they even progress from the initial form submission, dramatically cutting lending costs and charge-offs.
Lead scoring
For financial institutions and lenders to SMBs, the results of poor lead qualification can have a severe negative impact.
It is difficult to determine the quality of leads while relying only on internal data such as form fills, website engagement, and pages visited. Enhancing existing datasets with real-time, relevant information enables the creation of new lead scoring models that will more accurately qualify leads and identify those with low-risk profiles.
The result is better targeting, improved conversions, streamlined operations, less time wasted pursuing bad leads, and less money spent on recovering defaulted loans that were extended to incorrectly qualified leads.
The types of alternative data that can help improve lead scoring models are:
- Corporate data that includes reliability indicators such as assets owned, liabilities, timely repayment of bills, and bankruptcy history
- Business ratings and reviews on social media
- Website data such as traffic and global traffic rank
- Social media presence and engagement data
In our series of bylines about external data use cases for fintech, it is evident that the right external data can help fintechs in many ways. The best way to ensure this is to use an end-to-end platform that not only connects you to thousands of relevant data signals, but also helps you integrate them into predictive BI or machine learning models. This way, you upload your dataset and enrich it with the most relevant details drawn from alternative, external sources.
Using a platform like Explorium enables data access, removes barriers to wider adoption of external data, and helps organizations establish their data strategies.
For more insights, download our white paper, The Definitive Guide to External Data for Fintech. Click here to learn more about how Explorium can help you find qualified prospects and accelerate sales through better data, and try it for free.