The roles of alternative data and machine learning in fintech lending: Evidence from the LendingClub consumer platform

• Author: Julapa Jagtiani,Catharine Lemieux
• DOI: http://doi.org/10.1111/fima.12295
• Date: 01 December 2019
• Published date: 01 December 2019

DOI: 10.1111/fima.12295

ORIGINAL ARTICLE

The roles of alternative data and machine learning

in fintech lending: Evidence from the LendingClub

consumer platform

Julapa Jagtiani1Catharine Lemieux2

1FederalReserve Bank of Philadelphia,

Philadelphia, Pennsylvania

2FederalReserve Bank of Chicago, Chicago,

Illinois

Correspondence

JulapaJagtiani, Federal Reserve of Philadelphia,

TenIndependence Hall, Philadelphia, PA19106.

Email:julapa.jagtiani@phil.frb.gov

Abstract

There have been concerns about the use of alternative data sources

by fintech lenders. Wecompare loans made by LendingClub and sim-

ilar loans that were originated by banks. The correlations between

therating grades (assigned by LendingClub) and the borrowers’ FICO

scores declined from about 80% (for loans originated in 2007) to

about 35% for recent vintages (originated in 2014–2015), indicat-

ing that nontraditional data (not already accounted for in the FICO

scores) have been increasingly used by fintech lenders. The rating

grades perform well in predicting loan default. The use of alterna-

tive data has allowed some borrowers who would have been classi-

fied as subprime bytraditional criteria to be slotted into “better” loan

grades, allowing them to obtain lower priced credit.

KEYWORDS

fintech, LendingClub, marketplace lending, alternative data, shadow

banking, P2P lending, peer-to-peer lending

1INTRODUCTION

Consumer credit has been growing steadily in recent years. As of September 2018, of the nearly $4 trillion of overall

consumer credit (not secured by real estate), approximately 26% was credit card debt and only 6% was unsecured

personal loans (FederalReserve, 2018).1Bricker et al. (2017) find that based on the 2016 Survey of Consumer Finance,

20.8% of families felt credit constrained, and this result has been fairly consistent over recent years. Oliver Wyman

(Carroll & Rehmani, 2017) estimates that as many as 60 million people may have been unable to access credit due to

their thin credit files or lack of credit history. It is likely that a significant number of consumers in the subprime pool

(based on the traditional measures) maynot be risky borrowers, but they were subject to excessive risk premiums that

reflect their low credit scores (based on inaccurate measures).

c

2019 Financial Management Association International

1Theremaining 68% was student loan and auto-related debt.

Financial Management. 2019;48:1009–1029. wileyonlinelibrary.com/journal/fima 1009

1010 JAGTIANIAND LEMIEUX

Fintech lending platforms have entered the unsecured personal loan space and havethe potential to fill this unmet

demand for credit. Over the past decade, online alternativelenders have evolved from platforms connecting individual

borrowers with individual lenders to sophisticated networks featuring institutional investors, direct lending (on their

balance sheet), and securitization transactions.2The use of alternative data sources, big data and machine learning

(ML) technology, and other complex artificial intelligence (AI) algorithms could also reduce the cost of making credit

decisions and/or credit monitoring and lower operating costs for lenders. Fintech lenders could potentially pass the

benefits on to borrowers.

Alternative data, when included in the credit risk analysis, could paint a fuller and more accurate picture regarding

people’s financial lives and their creditworthiness that could make it possible for millions of American consumers to

have access to affordable credit (Cordray,2017). Some fintech lenders have developed their own proprietary complex

ML algorithms that use big data and alternative data to evaluate borrowers’ credit risk. Through this new approach

to credit risk evaluation, some consumers with a short credit history (i.e., one that may not satisfy a bank’s traditional

lending requirements) could potentially obtain a loan from an online alternative lender.Some fintech lenders special-

ize in making loans to those “below-prime” consumers by identifying those “invisible prime” consumers from the (tra-

ditional) subprime pool. Fintech lenders could potentially make loans to below-prime consumers at lower costs than

what they would have otherwise received and without the lenders incurring any more loss (because of loan default)

than the expected levelof loss on loans to average consumers.

Crosman (2016) reports in American Banker that SoFi no longer uses FICO scores when determining loan qualifica-

tions. In addition, Kabbage claims that FICO scores are not part of its creditworthiness determination (although FICO

scores are used for benchmarking and investor reporting). In the American Banker article, Ron Suber,former president

of Prosper Marketplace,states that “Prosper gets 500 pieces of data on each borrower; the FICO score is just one data

point.” The company uses FICO scores to screen borrower candidates. A score of at least 640 is needed to be consid-

ered for a loan. Prosper analyzes additional data to determine its ultimate credit decision. These data sources were not

normally used by traditional lenders.

We use personal installment loan-leveldata from LendingClub’s unsecured consumer platform and compare it with

similar loan-leveldata from traditional lenders to explore the potential consumer benefits that fintech lenders provide.

Specifically,we investigate two channels: (a) whether the use of alternative data (to build internal credit rating systems

such as the one designed by LendingClub)can improve consumers’ ability to access credit by allowing lenders to better

assess their true creditworthiness and (b) whether the use of alternative data allows fintech lenders to better risk

price credit so some borrowers can get loans from fintech firms at a lower cost than they could get from traditional

banks.

Our results indicate that, over the years, alternative sources of information havebeen increasingly used by fintech

lenders to evaluate credit applications. The additional information is outside what is typically included in traditional

credit ratings or the traditionalcredit approval criteria. Our results demonstrate that the correlation between the bor-

rowers’ FICO scores (at the time of loan application) and the rating grades assigned byLendingClub have dramatically

declined over the years indicating an increased usage of alternative data in the internal rating process. We also find

that credit spreads can be explainedby information in LendingClub’s rating grades that are not found in the FICO score

or in other obvious measures of credit risk. This orthogonal component is also useful in predicting LendingClub’sloan

performance over the 2 yearsafter loan origination.

Although it is not known exactly what specific set of alternative data is used by each of the specific fintech lenders,

some havementioned information drawn from bank account transactions, such as utility or rent payments, other recur-

ring transactions,and electronic records of deposit and withdrawal transactions. Other items mentioned include insur-

ance claims, credit card transactions, a consumer’s occupation or details about their education, their use of mobile

phones and related activities, Internet footprints, online shopping habits, investment choices, and so on. Concerns

2Thisis frequently referred to in prior research as peer-to-peer (P2P).