Daniel Hinkson and Ryan Thorpe are the data science department at Crest Financial, an alternative lending firm providing borrowers with “No Credit Needed” financing.

One of the nation’s largest and fastest growing “No Credit Needed” lease-to-own companies, Crest Financial offers technology-driven instant approvals for items like furniture, appliances, tires, and personal medical devices on transactions up to $5,000. Crest is committed to providing more opportunity for customers, more success for retailers, more service to the community, and more growth for employees than any other company in their industry

.

Underwriting decisions are based on basic data supplied by the customer, and supplemented with payment histories like rent and utilities. Crest relies on predictive models created by Daniel and Ryan to help present a solid option to consumers with no access to traditional credit or financing.

Data science is mission-critical for the company, and Daniel and Ryan are vital to Crest’s future success. When it comes to underwriting and repayment predictions, the stakes are high – bad lending decisions impact the company’s bottom line. The quality, accuracy and volume of data science results generated by this dynamic duo are critical to Crest’s decision-making process.

The Quandary

Despite their heroic efforts, Daniel and Ryan were hampered by traditional data science methods, where building and testing machine learning models manually often took months, and deployment delays were common. To keep up with the ever-increasing workload, and to deliver faster, more accurate lending decisions, Crest needed a vastly-improved predictive modeling solution that would be not only accurate, but lightning-quick as well.

Looking for help, Daniel and Ryan sent out the DataRobot Signal.

Daniel and Ryan worked with the DataRobot team to evaluate the DataRobot platform on Amazon Web Services (AWS). Crest wanted to see how DataRobot on AWS could help them improve risk analysis, better identify marketing targets, and improve and expedite detection of fraudulent applications.

The results from less than an hour of proof-of-concept testing showed DataRobot models delivering better accuracy than the hand-built models developed over many weeks. Crest Financial was all in, quickly becoming a part of DataRobot's data science superhero universe.

DataRobot’s automated machine learning platform captures the knowledge, experience, and best practices of the world’s leading data scientists to deliver unmatched levels of productivity and ease-of-use for machine learning initiatives. With DataRobot’s help, Daniel and Ryan supercharged their efforts, providing more accurate underwriting decisions, and more timely support for their retail partners and the customers they serve.

With DataRobot, Daniel and Ryan quickly discovered their data science superpowers and transformed into data science superheroes. With their newfound abilities, Daniel and Ryan have the power to develop and deploy predictive models with lightning speed. Now they can:

• Pinpoint the right type of consumer for Crest in a high-risk and highly-competitive market.
• Quickly identify instances where applicants are attempting to obtain financing through fraudulent means.
• Accurately predict the likelihood of default for applicants.