ZestFinance Introduces Machine Learning Platform to Underwrite Millennials and Other Consumers with Limited Credit History

ZAML Platform helps lenders harness artificial intelligence to increase approval rates

LOS ANGELES--()--Today, ZestFinance announced the Zest Automated Machine Learning (ZAML™) Platform for credit underwriting. ZAML enables lenders to analyze vast amounts of non-traditional credit data to increase approval rates and reduce the risk of credit decisions, particularly for thin-file and no-file borrowers like millennials. The platform also provides the ability to explain data modeling results to measure business impact and comply with regulatory requirements. The ZAML Platform is available today.

Financial institutions, including banks, credit card issuers, auto financiers, and others, are under competitive pressure to increase revenues while managing risk and ensuring compliance. Expanding credit to new borrowers, particularly to millennials who are financing their first major purchases or looking for their first credit cards, is an effective way to build new markets.

“The difficulty financial institutions face underwriting millennials is their limited credit histories -- they’re a classic example of thin-file or no-file borrowers,” said Douglas Merrill, Founder and CEO of ZestFinance. “Traditional underwriting works well when evaluating borrowers with long credit histories, but when there is limited data, it can’t differentiate between creditworthy and high-risk applicants. Machine learning fills those gaps by analyzing a vastly broader set of data.”

Solving the Millennial Credit Problem

Traditional underwriting systems make credit decisions using a limited number of data points, primarily from credit bureaus. However, many millennials have no credit history or have missing and inaccurate data in their credit files. As a result, they are denied credit because they cannot be underwritten by traditional systems. However, many of those applicants would actually perform as well as prime borrowers. Thus, financial institutions minimize their risk by denying them credit, but also forgo profitable growth they require in today’s competitive marketplace.

Unlike traditional underwriting methods, ZAML uses machine learning to analyze tens of thousands of nontraditional and traditional variables to more accurately score borrowers, including thin-file and no-file borrowers. ZAML can analyze vast amounts of data they already have in-house, such as customer support data, payment histories, and purchase transactions. The platform can also add traditional credit information and nontraditional credit variables, such as how a customer fills out a form, how they navigate a lender’s site, and more.

For example, Baidu, the leading Chinese language Internet search provider, partnered with ZestFinance in its effort to turn Baidu's search, location, and payment data into credit scores.

"Artificial Intelligence is the new electricity. It’s transforming industry after industry, and financial services are particularly ripe for innovation. We will see tremendous change in a variety of financial sectors in the U.S. and abroad because of the AI work of companies like ZestFinance," said Andrew Ng, Chief Scientist at Baidu.

About ZAML

ZAML is the only machine learning platform developed specifically for credit underwriting. Since 2009, ZestFinance has used machine learning and big data to reduce risk in credit underwriting, and that technology is the foundation of ZAML. The platform uses Google-like algorithms to analyze tens of thousands of data points to provide a richer, more accurate understanding of all potential borrowers, delivered in an easy-to-use web interface.

The ZAML Platform consists of three components:

  • data assimilation, which identifies, cleans and aggregates data from thousands of sources, regardless of format, and provides APIs for loading and leveraging internal data;
  • modeling tools that help lenders train, ensemble and productionalize machine learning models that address specific business challenges such as fraud or marketing; and
  • model explainability tools that identify key model elements, highlight potential modeling errors, and provide transparency into machine learning models. ZAML’s explainability tools are particularly important as they both help lenders understand a model's economic value to communicate it within their organizations, and provide a way to ensure compliance with regulations on disparate impact and adverse action.

Pricing and availability

The ZAML Platform is available today. Pricing varies by organization, need and usage of the technology.

About ZestFinance

ZestFinance, Inc. applies its unique credit-decisioning technology platform — based on data science and machine learning — to help lenders effectively predict credit risk so they can increase revenues, reduce risk and ensure compliance. ZestFinance was founded in 2009 by Douglas Merrill and a team of former Google employees with the mission of making fair and transparent credit available to everyone. The company is headquartered in Los Angeles, California. For more information, visit www.ZestFinance.com.


Cutline Communications
Sarah Arvizo

Release Summary

ZestFinance launched the Zest Automated Machine Learning (ZAML™) Platform to help lenders underwrite millennials and other consumers with limited credit history.


Cutline Communications
Sarah Arvizo