The ‘game-changing’ initiative follows successful tests which proved sophisticated algorithms could slash the risk of defaults compared to traditional risk management methods.
Machine learning tools analyze data more deeply and in more detail. They also are capable of ‘learning’ over time and making changes to systems as patterns evolve or emerge, or if they recognise key external trends, such as economic shifts.
The trial, carried out in partnership with ZestFinance, measured the effectiveness of machine learning in predicting risk in auto financing, including customer segments with limited credit histories.
Ford Credit’s proprietary models have performed well for decades and the company is an industry leader in automotive risk management.
The machine learning study compared results from a Ford Credit scoring model with a machine learning model developed by ZestFinance using its underwriting platform to do deeper analysis of applicant data.
The study found that machine learning-based underwriting could reduce future credit losses “significantly” and potentially improve approval rates for qualified consumers, while maintaining consistent underwriting standards.
Ford Credit chairman and CEO Joy Falotico said: “At Ford and Ford Credit, our primary goal is to serve our customers.
“For this study, we worked with ZestFinance to harness the capability of machine learning to analyze more data and to analyze our data differently. The study showed improved predictive power, which holds promise for more approvals, enhanced customer experiences and even stronger business performance, including lower credit losses.”
Successful use of machine learning could open up auto financing services to millions of consumers with limited credit histories who might have been denied loans under current procedures.
According to the U.S. Consumer Financial Protection Bureau, 26 million American adults, or about one in 10, have no credit record, making them difficult and often impossible to underwrite using traditional methods.
This includes millions of millennials who are also part of the fastest-growing segment of new car buyers. Last year, new vehicles purchased by millennials represented 29% of all US sales, and that number is expected to grow to 40% by 2020.
Although these consumers may have steady jobs, their creditworthiness is heavily based on credit history. This makes it more difficult for companies to provide financing, and they could miss an opportunity for revenue growth.
ZestFinance founder and CEO Douglas Merrill said: “Machine learning-based underwriting will be a game-changer for lenders, opening entirely new revenue streams.
“Millennials offer the perfect example. They are typically a good credit risk and are expected to command $1.4 trillion in spending by 2020, but many lack the financial history needed to pass a traditional credit check.
“Applying better math and more data to traditional underwriting illuminates the true credit risk and helps forward-looking companies like Ford Credit continue to grow their businesses while predictably managing their risk.”
ZestFinance is now offering the Zest automated machine learning platform, which it developed specifically for credit underwriting.
It consists of three components: data collection and assimilation, machine learning modeling tools, and transparency tools that enable companies to explain credit decisions.