Examples of AI Application in Automotive Lending (Case Studies)

Some example studies of companies where AI is being used to facilitate automotive lending provided involve Ford Credit Motor and PointPredictive. PointPredictive works with various auto lenders to fight against fraud through machine learning technology that helps recognize fraudulent patterns in loan applications. Meanwhile, Ford Credit is testing machine learning technology for its auto loan services.


  • PointPredictive unveiled its brand-new Synthetic ID Alert in 2018 to provide assistance to auto-lenders in discerning deceptive accounts produced through the use of synthetic identities.
  • It creates alerts to flag auto-loan applications imitating patterns similar to synthetic ID fraud.
  • Synthetic ID Alert was tested on more than 40 million actual auto-loan applications. The solution, which is machine based, can be equipped in the technology system of a lender without difficulty and utilized in application evaluation in real time.
  • At the Automotive Intelligence Summit in 2019, PointPredictive received recognition as a part of the first ‘Emerging 8’ group of innovative businesses providing effective solutions directly to the automotive lending sector. PointPredictive was acknowledged for its best in class solutions, including the Income Validation Alert, Auto Fraud Manager, and Synthetic ID Alert.
  • The company works with auto lenders to counter the $7 billion yearly fraud risk issue. It does this by facilitating the auto lenders to administer machine learning technology to detect and prognosticate signs of deception in loan applications.

Ford Motor Credit

  • In the year 2017, Ford Credit worked with ZestFinance and shared the results of an investigation gauging the efficacy of machine learning to anticipate risk within auto financing better and conceivably augment auto financing for many Americans, including Millennials, who have insufficient credit histories.
  • The company organized efforts to administer machine learning models to advance its vigilant and reasonable lending process.
  • The study showed that underwriting based on machine learning is capable of diminishing credit losses in the future considerably and likely enhancing approval rates for several qualified individuals, while preserving its regular underwriting specifications.
  • Ford Credit’s Joy Falotico (CEO and Chairman) stated that the company collaborated with ZestFinance to utilize the capacity of machine learning to examine more information and interpret their data in another way. Their evaluation revealed stronger predictive power, which indicated what Falotico says is a possibility for improved business performance (e.g., lower credit losses), enhanced customer experience, and additional approvals.


  • Aclaró’s artificial intelligence system, TrueView, evaluates a lender’s loan portfolio and risk. So far the system has shown strong success: “the average risk evaluation analysis of a portfolio which contains 10,000 loans is completed in under 30 seconds” and “in blind tests, Aclaró TrueView averaged a 97 percent success rate in identifying whether a loan would be paid off or written off.” Since Aclaró’s recent acceptance into the Microsoft Partner Network, the system’s speed and accuracy should only increase.
  • Aclaró’s primary objective was to advance fair lending by assisting smaller lenders in mitigating risk and extending the lifespan value of its existing borrowers. It seems Aclaró has succeeded in this area, their customers including both big and small lenders.
  • Aclaró has continued to develop their artificial intelligence and programs, one recent development the Marketplace, which connects auto dealers and lenders. Through this, lenders gain a better sense of the borrower’s cash flow, financial information, and their probability of paying back the loan in full.
  • Already, the Aclaró suite of tools has aided lenders in gaining a better understanding of borrowers’ proclivity to purchase, cash flow information, and probability of repaying the loan in full. Lenders have been able to provide more tailored loans for cars that consumers really desire as a result of these findings.
  • Aclaró’s TrueView and Marketplace are currently available. The system’s most recent update was on September 10, 2019, now allowing lenders to view and consider a borrower’s cash flow.


  • ZestFinance uses machine learning to help more people get approved loans, which would strengthen their fair lending by providing credit for borrowers overlooked by traditional credit models. One of ZestFinance’s primary goals was to expand credit services to potential borrowers without a credit score. ZestFinance accomplishes this by taking into account factors that credit scores typically overlook, such as application data or CRM data…customer call center history, residence history, or whether the applicant has any pending court cases that, depending on how they resolve, may have an effect on the applicant’s financial standing.
  • ZestFinance has experienced significant success with the approach, approving 14% more applications without taking on extra risk. This gives borrowers with poor or nonexistent credit access to loans without risk to the lenders.
  • ZestFinance has worked with Prestige, which saw a “36% increase in new applicants and a 14% increase in borrower approvals” after using ZestFinance with no added risk. Ford Motor Credit Company reported comparable results, stating that the research demonstrated increased predictive power, which bodes well for more approvals, better customer experiences, and enhanced company performance, including reduced credit losses.
  • ZestFinance is currently available for use, the company offering two systems for lenders: ZAML Platinum and ZAML Silver, which differ in customizability and features like hosting location (on the premises or in the cloud). Both systems come with advanced compliance tools like “automated MRM reports, fair lending and economic impact analysis.”


  • Upstart uses “AI to determine creditworthiness and streamline the loan process.” Their main focus is “younger adults who lack much credit history,” whom they include by considering “education, SAT scores, GPA, field of study, and job history.” Their approach succeeded, achieving lower loss rates while simultaneously approving twice as many borrowers. This system strengthens their fair lending as it does not exclude trustworthy borrowers simply on account of their lack of a credit history.
  • Its platform collects consumer credit demand and links it to a network of artificial intelligence-enabled bank partners. It takes education, cost of living, and a variety of other variables into account when making loan choices rather than depending only on credit scores.
  • While Upstart is primarily concerned with providing a general alternative to a FICO credit score, Upstart’s CEO and Co-Founder says Upstart plans to offer other products in the future, including auto loans.
  • Upstart’s other AI loaning tools are currently available, but a system specifically for automotive lending is only planned, and no announcements on development or launch have been made yet.
Previous Post
Next Post