Mitigating Application Fraud Risk for Online Lenders

Improve fraud detection models to cut down on fraudulent applications

Internationally, fraud is at an all-time high. PwC’s Global Crime and Fraud Survey 2020 found that nearly half of all businesses had experienced fraud in the previous two years, with an accumulated cost of $42 billion.
The problem

Online lenders experience about twice as much fraud as banks do. For fintechs, 6% of loans are made to fraudulent business borrowers. Online lenders are targets for fraud by borrowers who claim to be legitimate businesses. Compared to banks, which generally make loans to known customers, the online application process is remote and decisions are made quickly. Several online lenders don’t do thorough background checks, and rely on basic information such as business and owner name, address, business IP address, and business creation date to make lending decisions.

The solution

Fintechs need more relevant, alternative data to better assess if a business is real. By enriching internal data with external data, lenders can generate more accurate fraud scoring models which can dynamically identify fraud by: 

  • Expanding the number of relevant data points used at the pre-qualification stage creating more accurate detection of fraudulent applications. 
  • Obtaining alternative risk scores based on a variety of economic and financial health data that indicates fraud risk. 
  • Being able to identify fictitious or non-existent businesses by leveraging online reviews and other social media and web data.
The results:

Increased detection of fraudulent loan applications

By leveraging alternative data for lending, fintechs can improve their ability to immediately pinpoint loan applicants faking their identities by flagging non-existent or fictitious businesses. A more nuanced predictive model can take into account online evidence of past fraud, including any alarm-bell-raising Yelp reviews or complaints about the business on social media. It can incorporate information from multiple regions, sources, and past vendor relationships to assess the validity of the applicant’s identity. With more accurate fraud detection models, one of our customers was able to boost their fraud detection rate by 92% on applications before they progressed from the initial form submission. This cut their lending costs and charge-offs by 15%.

Reduce costs and detect fraudulent loan applications using augmented data discovery.

Other resources you might be interested in

Case Studies: Melio Payments Case Study

Explorium Case Study - Melio is on a mission to keep small businesses in business by providing a smart, simple B2B payments solution tailor-made for their needs.

One-pagers: Explorium for Risk and Fraud

Fight risk with the data you need, not the data you have. Learn all about how Explorium supports risk and fraud use cases with external data and signals for better ML models.

Case Studies: Behalf Case Study

Behalf Uses Explorium-sourced Data to Accurately Segment Potential Business Customers, Improving Marketing Efficiency and Streamlining Operations

Get started with Explorium External Data Cloud Start for free