LendingClub is built on data. We use it in every aspect of our business – from operations, to credit, to the way we hire employees – and as the basis for continued innovation on behalf of investors and borrowers alike.
Starting September 8, 2017, we are rolling out the fifth-generation credit model, which further leverages machine learning and 10 years of LendingClub data to better assess and price credit risk. The model went live for certain borrowers on September 8 and was ramped up to the vast majority of borrowers a few days after. (A small borrower segment will continue to be evaluated under the prior credit model and we are working to roll it out for those borrowers next year.) LendingClub has helped 1.5+ million borrowers since 2007; each borrower provides unique insight that can be leveraged in future credit decisions.
The new credit model is the latest in LendingClub’s long history of innovation: it’s a more powerful, complex, multi-variable model that takes advantage of a wealth of proprietary data and best-in-class modeling techniques. It’s more predictive than a borrower’s FICO score alone, and is 24% better at differentiating the likelihood of a borrower charging off than the fourth-generation model.
Going Beyond FICO
The fifth-generation credit model continues a long tradition of innovating beyond traditional FICO-based underwriting.
It’s why we are able to improve financial inclusion and increase access to lower interest rates for borrowers. Through powerful models we are better able to assess risk: we can facilitate loans to people who traditional lending programs miscategorize as too risky but are actually good borrowers, as well as screen out borrowers who seem safe but we believe are risky based on our use of rich data. A recent study done by researchers from the Federal Reserve emphasized these results and found that LendingClub “has enhanced financial inclusion and allowed some borrowers to be assigned better loan ratings and receive lower priced credit.”
Highlights of the New Model
Since our founding in 2007, we have used data to our advantage. The latest credit model is built on the most extensive data set ever and validated on recent data, which allows the model to better reflect the current environment. It also leverages the longest track record in the industry – LendingClub has rich data based on the last 10 years of underwriting.
The fifth-generation model specifically distinguishes itself from earlier models using more unique data and machine learning techniques:
Impact to Investor Returns
The new model is 24% better at differentiating the likelihood of a borrower charging off than the fourth-generation model. This means the model better assesses and prices an individual borrower’s risk in addition to the risk of the total population.
In total, we expect that investors will see more lower-risk borrowers on the platform. Some higher-risk borrowers who may have received an offer previously will be screened out, while other borrowers will qualify for lower prices. The end result is that loan volume will shift toward higher quality grades (grades A and B) overall. Projected investor returns are mostly unchanged by grade and term, ranging from 4-9%. Expected charge-off rates for the platform as a whole are going down slightly (from 6.2% to 6.0%) as we expect to see more lower-risk borrowers on the platform as a whole.1
See the table below for projected returns by grade and term.
We see the fifth-generation credit model as the latest innovation in our continuous enhancement cycle, and one that helps us continue to serve borrowers and provide investors with solid risk-adjusted returns.
Safe Harbor Statement
Some of the statements above are “forward-looking statements.” The words “anticipate,” “believe,” “estimate,” “expect,” “intend,” “may,” “outlook,” “plan,” “predict,” “project,” “will,” “would” and similar expressions may identify forward-looking statements, although not all forward-looking statements contain these identifying words. Actual performance of the overall platform has differed from projected performance in the past, and could differ in the future. Factors that could cause actual results to differ materially from those contemplated by these forward statements include: increases to unemployment rates, particularly if such increases are concentrated in populations with a greater propensity to take loans facilitated by our platform; changes to consumer credit behaviors; stagnation or reduction in the growth of the nation’s gross domestic product or uncertainties created by political changes associated with a change in presidential administrations, the Company’s ability to continue to attract and retain new and existing retail and institutional investors; competition; and demand for the types of loans facilitated by the Company and those factors set forth in the section titled “Risk Factors” in the Annual Report on Form 10-K, filed with the SEC. LendingClub may not actually achieve the plans, intentions or expectations disclosed in forward-looking statements, and you should not place undue reliance on forward-looking statements. Actual results or events could differ materially from the plans, intentions and expectations disclosed in forward-looking statements. LendingClub does not assume any obligation to update any forward-looking statements, whether as a result of new information, future events or otherwise, except as required by law.
A recent LendingClub member survey revealed more than half of Americans (55%) will probably take debt accumulated over the…READ MORE
Even as the U.S. economy continues to put in a strong showing, with key indicators such as payrolls and…READ MORE