ZestFinance and the Nuances of Modeling Credit Risk

Pando Daily has a post about Peter Thiel leading a $20 million funding round for a four year old company called ZestFinance. Their goal is to better predict consumer behavior. They model more than 10,000 data points and arrive at more than 70,000 potential signals of consumer behavior. This was the most interesting bit in the article:

Not all signals are obvious, Merrill explains, noting for example that the way a consumer types their name in the credit application – using all lowercase, all uppercase, or correct case – can be a predictor of credit risk. Other seemingly trivial data points include whether an applicant has read a letter on the company’s website and whether the applicant has a pre-paid or post-paid cell phone.

ZestFinance had evolved its business model to that of an underwriting service provider to third-party subprime lenders, “exiting the lending business to avoid the appearance of competition with its new partners.” Will be interesting to see if their methodology gains acceptance in the wider banking sector in the years to come.

Read the entire post here.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s