1、 BIS Working Papers No 1041 The impact of fintech lending on credit access for U.S.small businesses by Giulio Cornelli,Jon Frost,Leonardo Gambacorta and Julapa Jagtiani Monetary and Economic Department September 2022 JEL classification:G18,G21,G28,L21.Keywords:fintech credit,peer-to-peer(P2P)lending

2、,marketplace lending,small business lending(SBL),Funding Circle,LendingClub,alternative data,credit access,credit scoring.BIS Working Papers are written by members of the Monetary and Economic Department of the Bank for International Settlements,and from time to time by other economists,and are publ

3、ished by the Bank.The papers are on subjects of topical interest and are technical in character.The views expressed in them are those of their authors and not necessarily the views of the BIS.This publication is available on the BIS website(www.bis.org).Bank for International Settlements 2022.All ri

4、ghts reserved.Brief excerpts may be reproduced or translated provided the source is stated.ISSN 1020-0959(print)ISSN 1682-7678(online)1 The Impact of Fintech Lending on Credit Access for U.S.Small Businesses By Giulio Cornelli,Jon Frost,Leonardo Gambacorta and Julapa Jagtiani Abstract Small business

5、 lending(SBL)plays an important role in funding productive investment and fostering local economic growth.Recently,nonbank lenders have gained market share in the SBL market in the United States,especially relative to community banks.Among nonbanks,fintech lenders have become particularly active,lev

6、eraging alternative data for their own internal credit scoring.We use proprietary loan-level data from two fintech SBL platforms(Funding Circle and LendingClub)to explore the characteristics of loans originated pre-pandemic(20162019).Our results show that fintech SBL platforms lent more in zip codes

7、 with higher unemployment rates and higher business bankruptcy filings.Moreover,fintech platforms internal credit scores were able to predict future loan performance more accurately than the traditional approach to credit scoring,particularly in areas with high unemployment.Using Y-14M loan-level ba

8、nk data,we also compare fintech SBL with traditional bank business cards in terms of credit access and interest rates.Overall,fintech lenders have a potential to create a more inclusive financial system,allowing small businesses that were less likely to receive credit through traditional lenders to

9、access credit and to do so at lower cost.Keywords:fintech credit,peer-to-peer(P2P)lending,marketplace lending,small business lending(SBL),Funding Circle,LendingClub,alternative data,credit access,credit scoring.JEL Classification:G18,G21,G28,L21.*Giulio Cornelli is with the Bank for International Se

10、ttlements(BIS)and the University of Zrich.Jon Frost is with the BIS and the Cambridge Centre for Alternative Finance.Leonardo Gambacorta is with the BIS and CEPR.Julapa Jagtiani is with the Federal Reserve Bank of Philadelphia.The authors thank Asani Sarkar,Barbara Lipman,Bill Spaniel,Mitchell Berli

11、n,Bob Hunt,and in particular Tommaso Oliviero for their helpful comments and suggestions.Thanks to Adam Lyko,Erik Dolson,and Drew Taylor for their research assistance,and to Nicola Faessler for support with typesetting.The opinions expressed in this paper are the authors own views and do not necessa

12、rily represent the views of the Federal Reserve Bank of Philadelphia,the Federal Reserve System,or the Bank for International Settlements.Any errors or omissions are the responsibility of the authors.2 1.Introduction Small business lending(SBL)plays an important role in funding productive investment

13、 and fostering local economic growth(Beck and Demirg-Kunt,2006).In the United States,community banks are known to have comparative advantages in SBL through their personal relationships with small business owners in their own local area.Until recently,the soft information that community banks have a

14、bout their local small businesses and business owners were not easily accessible to outside lenders.Of the approximately 6,000 banks in the United States,about 90 percent are small local banks that exist to serve the people and businesses in their local community.In the last several years,the financ

15、ial landscape for SBL has changed significantly.Fintech lenders and other technology companies have shaken up the traditional ways of doing business.Lending by fintech and big tech firms has become increasingly important as a source of finance for both consumers and small businesses around the world

16、;see Financial Stability Board(2019),Cornelli et al.(2019;2020)and Ziegler et al.(2020).Soft information about businesses and entrepreneurs can now be obtained from nontraditional channels.For example,customer ratings and satisfaction about businesses may be available online.Information on the credi

17、bility and reputation of business owners is also available through several data aggregators and artificial intelligence(AI)/machine learning(ML)vendors.In addition,through their use of digital platforms,some lenders can incorporate various types of alternative data,including those related to online

18、footprints,phone and email history,location,etc.Digital platforms have allowed fintech lenders to serve borrowers that may otherwise be unserved or underserved by incumbent financial institutions,even in economies with relatively deep credit markets,like the United States.While it seems that large U

19、.S.banks have been increasing their SBL activities,this is true only when compared with the overall banking industry.The origination and funding of SBL overall has shifted dramatically over the past several years toward the nonbank(“shadow banking”)sector.This is partly because of the increased regu

20、latory burden since the financial crisis(eg,from the DoddFrank Act of 2010 and the rising cost of small loan origination).While nonbank lenders are subject to some consumer protection and other compliance requirements,they are not subject to the same rigorous supervisory examination as banks,allowin

21、g nonbank lenders to compete with banks in SBL.1 At the same time,technological advances and the post-crisis pressure on bank business models may also be important drivers to the shift.Fintech lenders have increasingly become an important part of the nonbank SBL sector.Funding Circle and LendingClub

22、 are examples of large fintech lenders that use big data and complex algorithms such as AI/ML models to evaluate the credit risk of small businesses and that of the business owners,2 and to make lending decisions at a much faster speed than traditional lenders.Research has shown that fintech lenders

23、 are more efficient in making consumer loans than traditional lenders operating at the same scale.For instance,Hughes,Jagtiani,and Moon(2022)find LendingClub to be more efficient for consumer loans than traditional peer lenders of the same size.One 1 Nonbank lenders are,however,subject to significan

24、tly higher funding cost than banks since they do not have access to low-cost funding through insured deposits.2 Fintech lenders,like Funding Circle and LendingClub,use AI/ML in developing the models that are ultimately presented in the form of traditionally structured logit regression models.Thus,th

25、ey are not black-box models but using more complex algorithms and more data to achieve credit decisions that would be explainable to investors and potentially regulators.3 factor that contributes to enhanced lending efficiency at fintech platforms is their ability to digitally collect and analyze no

26、ntraditional data,including what used to be referred to as soft information in relationship lending.This allows them to capture a more complete financial picture of the borrowers than traditional lenders can.This can improve access to credit.Jagtiani and Lemieux(2018,2019)find that fintech lenders h

27、ave helped some below-prime consumers to gain greater access to credit and at a lower cost,compared with what they would have been able to get through traditional channels.Alternative data,which have been increasingly used by lenders to identify the“invisible prime”or“hidden prime”borrowers in consu

28、mer lending,have also been used to price credit risk in SBL.However,empirical evidence on fintech lending efficiency has so far focused on consumer credit.In this paper,we explore the roles of alternative data and the impact on credit access to small businesses.In the United States,some fintech lend

29、ers have competed successfully with community banks.In addition,fintech lenders have also helped to fill the SBL credit gap in certain communities because of the SBL pullback and reduced market share by traditional banks.Fintech lenders often have access to their own proprietary big data from paymen

30、t platforms that gives them a birds-eye view of the business,industry,and location in which a firm operates.Several big tech payment platforms,such as Amazon,and fintech payment firms,such as Square3 and PayPal,have also lent to business owners who may have thin credit files,but whose cash flows and

31、 payment transactions have been established through their payment platform.Other fintech SBL lenders,such as Kabbage,OnDeck,Funding Circle,and LendingClub use other alternative data in their lending decisions(Goldstein,Jagtiani,and Klein(2019).4 The higher cost of originating small loans has been ov

32、ercome through a digitized credit application and decision process,where the fixed cost of originating small short-term business loans has become trivial,relative to the cost incurred by traditional lenders.However,there have also been concerns about the potential impact of these disruptive business

33、 models on consumers,business owners,and financial stability,especially if the fintech credit scoring techniques do not prove to be valid in a different stage of the economic or financial cycle(such as a deep recession).In this paper,we focus on fintech SBL,which is similar to SBL originated by trad

34、itional lenders,eg with comparable interest rates and loan maturities as those offered by banks.We explore the capacity of fintech firms to facilitate access to credit for small business owners who are headquartered in less financially developed areas and assess the subsequent performance of such lo

35、ans.Specifically,we ask the following research questions.Has fintech lending enhanced credit access to small 3 In December 2021,Square rebranded itself and changed its name to“Block,”as the group aims to emphasise business lines beyond its seller business(still branded as Square).Its ticker on the N

36、ew York Stock Exchange will remain SQ at least for some periods of time.This rebranding is like that of other big-tech firms,such as Google that placed itself under the parent company Alphabet in 2015 and Facebook placing itself under parent company Meta in October 2021.4 During the coronavirus Pand

37、emic,several fintech SBL lenders(namely,Square,PayPal,Intuit Quickbooks,Funding Circle,and OnDeck)received approval by the U.S.regulators to originate Paycheck Protection Program(PPP)loans to small businesses under the CARES Act of March 2020.Other fintech platforms(which received the approval much

38、later)worked with partner banks(such as Cross River Bank,Celtic Bank,Radius Bank,and Sunrise Banks)to assist with the PPP loan approval and origination in the first round of PPP.4 business owners who are likely to be“underserved”by traditional lenders?Are there measurable differences in the informat

39、ion contents in credit scores assigned by fintech lenders versus those assigned by traditional credit rating agencies?What is the added value of alternative data in credit risk evaluation and lending decisions?To do this,we use detailed microdata from Funding Circles small business platform,and we c

40、ompare this with the LendingClub SBL fintech platform,and then compare with traditional lending using data on(business)credit cards from Y-14M(submitted monthly to the Federal Reserve by CCAR banks for stress testing purposes).First,our results show that,also in the SBL space(in addition to consumer

41、 lending),fintech lenders can serve borrowers who were less likely to receive credit from traditional banks and that they employ alternative data to improve their credit risk evaluation and scoring.Second,more specifically,we find that fintech SBL platforms lent more in zip codes with higher unemplo

42、yment rates and higher business bankruptcy filings.Third,our results confirm that fintech platforms internal credit scores were able to predict future loan performance more accurately than the traditional approach to credit scoring(including both credit rating of the business owners and credit ratin

43、g of the business itself).Fourth,we find that this enhancement ie;the divergence of fintech scores from traditional credit scores and the improvement in predicting credit delinquencies were particularly stronger in areas with high unemployment rate.Fifth,using Y-14M loan-level bank data(on tradition

44、al bank business cards)to compare with fintech SBL in terms of credit access and interest rates,our results confirm that fintech lenders provide credit to additional small business borrowers at lower cost.It is important to note that our results in this paper,based on two specific fintech lenders,ma

45、y not be applicable to the entire fintech lending industry.While these lenders played an important role in the fintech SBL market during the period of analysis,they may not be representative for the whole sector.Moreover,not all SBL products are the same,and they could have a dramatically different

46、impact on borrowers and the economy overall.For example,some fintech lenders specialize in very small and short-term loans,with the intention to help business owners deal with unexpected liquidity needs.Other fintech lenders specialize in longer-term loans like those provided and supported by the U.

47、S.Small Business Administration(SBA).Within the fintech SBL space in the United States,loan products vary significantly in terms of loan amounts($5,000 to$500,000),maturity(60 days to five years or longer),interest rates(7 percent to 200 percent annual percentage rate(APR),and other features.Still,t

48、he use of proprietary data from two major fintech lenders,and a comparison with supervisory data from U.S.banks,allow for a more granular view of fintech credit than has been available in the past.5 This represents one step in a broader research agenda.The rest of the paper is organized as follows.S

49、ection II reviews the literature and discusses findings that are especially relevant to the roles of fintech in SBL.Section III describes the proprietary loan-level data from Funding Circles small business lending platform.This section highlights stylized facts and presents summary statistics of the

50、 data.We compare some of these facts with aggregate data from the LendingClub SBL platform and from Y-14M bankcard data from the CCAR monthly submission,to evaluate differences.Section IV discusses the empirical findings related to the roles 5 The two data sets(Funding Circle and LendingClub)used fo

51、r this paper represent fintech lenders that offer interest rate in the lower end of the spectrum.Both also have their own self-imposed interest rate ceiling of 36 percent APR,with loan maturities ranging from one to five years.5 of alternative data in fintech SBL and the impact on small business own

52、ers to access funding.Section V discusses conclusions and policy implications.2.Related literature There is a growing body of research on the drivers of fintech consumer credit,on the impact on credit access by consumers and on consumer privacy.However,the literature has been sparse on fintech SBL a

53、nd how it impacts credit access by small businesses,small firm performance,local communities and the overall banking and economic outcomes.This section provides an overview.A branch of the fintech literature has attempted to investigate the impact of fintech lending on credit access,and in some case

54、s,asking if fintech lending is a substitute or complement to bank credit.For U.S.consumer credit markets,Jagtiani and Lemieux(2018)find that LendingClub consumer lending has penetrated areas underserved by traditional banks(eg,in highly concentrated markets and areas with fewer bank branches per cap

55、ita).As for fintech mortgage lending,Jagtiani,Lambie-Hanson,and Lambie-Hanson(2021)find that mortgage loans are more likely to be originated by a fintech lender in areas in which there was a higher mortgage denial rate by traditional lenders in the previous period.Similarly,for access to business cr

56、edit,Erel and Liebersohn(2021)examine fintech lending to small businesses through the Paycheck Protection Program(PPP)in the U.S.during the pandemic.They find that fintech was disproportionately used in zip codes with fewer bank branches,lower incomes,and more minority households,and by small busine

57、sses with fewer banking relationships.6 Another paper that examines the PPP program is Howell,Kuchler,Snitkof,Stroebel,and Wong(2022).They find that fintech SBL lenders had a higher minority share among the PPP loans and that fintech can reduce racial disparities among small business owners.Regardin

58、g complementary or substitution,Dolson and Jagtiani(2021)find that,for both personal loans and mortgage loans,fintech lenders are more likely than other lenders(including both banks and other non-bank lenders)to reach out and offer credit to non-prime consumers,supporting the complementary hypothesi

59、s.Tang(2019)finds that online lending substitutes for bank lending by serving marginal borrowers in the United States,but it complements bank lending with respect to small loans.De Roure,Pelizzon,and Tasca(2016)use credit market data in Germany,and they show that fintech lenders serve the segment of

60、 riskier consumers who need small loans and are underserved by traditional banks.Thus,they conclude that fintech lenders substitute traditional banks for high-risk consumer loans.Much of the literature looks at the role of alternative data,including factors not traditionally considered to be closely

61、 related to the ability to pay(eg,digital footprints(Berg,Burg,Gombovi,and Puri(2020).7 Another strand of literature compares the behavior and pricing of fintech lenders with that of traditional banks.Buchak,Matvos,Piskorski,and Seru(2018)compare the pricing of online(fintech)lenders in the U.S.mort

62、gage market with that of banks and 6 The PPP was created by the U.S.government as a response to the lockdown during the COVID-19 pandemic.It was intended to assist small business owners by giving out loans to small businesses to keep their employees on their payroll during the pandemic.The loans wou

63、ld be forgiven if they were used for the intended purposes.7 See also Allen,Gu,and Jagtiani(2021)for a comprehensive literature survey of fintech research.6 (non-fintech)shadow banks.They find that fintech lenders charge a premium of 1416 basis points relative to bank mortgages.The reason is that fi

64、ntech lenders use more comprehensive data about consumers to identify those who likely prioritize convenience and faster services and are willing to pay a premium.Jagtiani,Lambie-Hanson,and Lambie-Hanson(2021)find consistent results for conventional mortgages but point to the opposite findings when

65、focusing only on Federal Housing Administration(FHA)loans.They conclude that conventional mortgage borrowers(who are generally well served in the financial system)tend to pay an interest rate premium to fintech lenders in exchange for convenience and faster services.FHA mortgage borrowers do not pay

66、 a premium rate but benefit from fintech lenders through increased funding access.8 Fuster,Plosser,Schnabel,and Vickery(2018)find that fintech mortgage lenders process loan applications about 20 percent faster than traditional lenders.Like mortgage borrowers,Mach,Carter,and Slattery(2014)find that p

67、eer-to-peer lenders charge a premium(up to two times higher)for small business lending when compared with traditional sources.Gambacorta,Huang,Li,Qiu,and Chen(2020)find that big-tech credit in China is less sensitive to house prices than bank credit,as big data take the place of collateral in mitiga

68、ting asymmetric information in the credit markets.Traditional business lending could introduce biases based on a loan officers perception of loan applicants,which affects loan approval and loan size.Carter,Shaw,Lam,and Wilson(2007)extract four criteria used by the loan officer and compare these with

69、 the sex of the loan applicant.Loan officers were more likely to assess female loan applicants on whether they had thoroughly researched the business,while male applicants were assessed more on whether they had thorough information about the business financial history,the business opportunity,and th

70、eir personal characteristics.Bellucci,Borisov,and Zazzaro(2010)find that female entrepreneurs face tighter credit availability but do not differ in interest rates to their male counterparts.They also find that female loan officers restrict credit to unestablished borrowers more than their male colle

71、agues.However,female loan officers are shown to ask female borrowers for collateral less often.Female loan officers are also more concerned with the applicants marital status than male counterparts,as it may suggest financial responsibility;see Carter,Shaw,Lam,and Wilson(2007).Atkins,Cook,and Seaman

72、s(2021)explore the impact of race using data from the PPP during the pandemic and find evidence supporting the hypothesis that fintech could reduce racial disparity in SBL.While Black-owned businesses received smaller PPP loans than White-owned businesses,the racial impact became smaller and later d

73、isappeared as changes were made to allow for entry by fintech firms in the second round of the PPP.Evidence of discrimination in SBL is apparent elsewhere,too.Borrowers at traditional lenders may be discouraged and simply not apply even if they need a further loan.Mijid and Bernasek(2013)calculate a

74、 38 percent loan denial rate for minorities and 14 percent for Whites,where firm and owner characteristics can explain 24 percentage points of loan denial.Bates and Robb(2015)find that firms in minority neighborhoods that need credit but do not apply are more common than firms that do apply for bank

75、 loans.Han,Fraser,and Storey(2009)find evidence that discouragement is an effective self-rationing mechanism.Risky borrowers filter themselves based on demographics of the entrepreneur and business.However,Cole and Sokolyk(2016)find that for every three discouraged firms,one would have been 8 FHA mo

76、rtgage borrowers are more likely to be underserved,based on lower average income and lower average risk scores,and they generally receive lower interest rates.7 approved for a loan had they applied.This represents a large inefficiency that fintech lending may help solve.Literature on the use of smal

77、l business credit scoring(SBCS)largely confirms that quantitative scoring has expanded credit availability to small businesses.Frame,Srinivasan,and Woosley(2001)find a positive relationship between the portfolio share of banks SBL and the use of credit scoring models.Berger and Frame(2007)also assoc

78、iate SBCS with expanded credit quantities,but they find that SBCS leads to greater average risk,along with increased lending to low-income areas,over greater distances,and longer loan maturity.The introduction of SBCS aimed to give investors a better understanding of borrower creditworthiness but le

79、aves out important information.Using only SBCS(ignoring a small business owners personal credit risk)could lead to inaccuracies in loan decisions.Community banks are known to rely on soft information for lending decisions,and they tend to use SBCS to supplement their credit decisions when evaluating

80、 small business credit.Berger,Cowan,and Frame(2011)confirm that community banks use SBCS but also find that they tend to use consumer credit scoring more than SBCS to evaluate small business loans.In addition,the use of alternative data and ML has been shown in several cases to improve credit assess

81、ments.Jagtiani and Lemieux(2019)find that rating grades from the LendingClub consumer platform(based on all available information including alternative data)perform well in predicting loan performance during the two years after loan origination date.The correlation between the rating grades and the

82、FICO scores declined over time from 2007 to 2015.Frost,Gambacorta,Huang,Shin,and Zbinden(2019)show evidence that nontraditional data from Mercado Libre in Argentina help to predict defaults relative to the traditional credit bureau.Lu(2018)examines the credit assessment at Ant Financial Services Gro

83、up(part of the Alibaba group,the largest fintech firm in China),which helps an online-based bank make a credit assessment in less than three minutes.MYbank(part of the Ant Financial Services)served over 20 million small businesses as of 2019.More than three-quarters of MYbank loan users had previous

84、ly never received business loans from traditional banks.By using the Alibaba e-commerce network to track small business trading history,MYbank is able to predict borrowers creditworthiness in minutes(with zero human interaction),while its competitors(mostly larger banks)refuse to lend to these small

85、 businesses due to their lack of sufficient credit information.Gambacorta,Huang,Qiu,and Wang(2019)find,with data from a Chinese fintech credit platform,that ML-based credit scoring was better able to predict default than traditional indicators after the 2017 regulatory shock in China.Another strand

86、of literature has looked at the impact of alternative data on credit access and firm performance.For example,Hau,Huang,Shan,and Sheng(2018)and Huang,Lin,Sheng,and Wei(2018)find that big-tech credit in China has reduced supply frictions in credit markets and that Chinese firms with access to big-tech

87、 credit experience higher performance than their small business firm peers.Dice and Liebersohn(2020)examine the response of fintech and nonbank lenders to financial services demand created by the introduction of the PPP during the COVID-19 pandemic.They find that online banks and nonbank financial i

88、nstitutions are disproportionately used by small businesses in areas with fewer banking services(measured by bank branches and businesses with little banking relationship)and that borrowers were more likely to get a fintech-enabled loan if they are in zip codes in which local banks were unlikely to

89、originate PPP loans.8 Overall,the efficiencies in digitizing various services by the banking industry can potentially improve upon or replace the traditional credit scoring and soft information at the center of relationship lending.By using big data on borrower demographics,nonbank lenders can imple

90、ment advanced algorithms to quickly and effectively risk-rank applicants.3.Data and stylized facts Fintech loan-level data We use proprietary data on fintech SBL from Funding Circle,and later LendingClub.The data set from Funding Circle contains loan-level data with a unique ID for each loan as well

91、 as characteristics of the loans and borrowers.This includes the credit rating of the business owner(FICO,VantageScore),the fintech credit rating of the business itself,firm-specific data(firm size,age,revenues,profitability,and number of employees),business funding needs(number of recent credit inq

92、uiries),and loan features(loan size,maturity,APR,fees,delinquency status,etc.).We then match local economic factors for each loan based on the zip code or county location of the loan.9 We also observe credit performance of each loan during the period of 24 months after its origination date.We flag t

93、he loan as being delinquent if it is at least 60 days past due(60+DPD)within the first 24 months after the origination date.Note that loan maturities vary,and they are generally three to five years.10 One important characteristic of our data set is that we observe several risk ratings of each loan.F

94、irst is the Business Owners Risk Score,which comprises the FICO and Vantage scores(ranging from 300 to 850)for the business owner as of the loan application date.Second,we observe the Business Risk Score,which is Experians Acquisition score assigned for the small business(rather than the small busin

95、ess owner).This scale looks different than the usual risk scores as the Acquisition Score is much more granular(from 100 to 100,000).Third,we observe the Risk Rating Assigned by Funding Circle,which ranges from A+to D.We use dummy variables in the regressions to indicate that the loans are rated by

96、Funding Circle as A-rated,B-rated,C-rated,or D-rated.The base case is the best rating assigned by Funding Circle,which is A+.Bank-level and county-level SBL data In addition,we collect SBL data from the Community Reinvestment Act(CRA)reports that banks file annually with federal regulators.Banks rep

97、ort the amount of SBL they 9 There are 41,683 zip codes in the United States,and 3,141 counties and equivalent entities.Thus,counties are generally larger.That said,zip codes can include parts of different counties;there is no one-to-one mapping.10 Of the more than 15,000 small business loans we hav

98、e from the Funding Circle platform,about 5 percent have a maturity of one year or less,and about 9 percent have a maturity of two years.The rest(about 86 percent of the loans)have a maturity of more than two years,with about 50 percent of all the loans being five-year loans.See Table A1 in the Appen

99、dix for more details.In general,Funding Circle loans have a longer maturity than loans from other SBL platforms.For LendingClub SBL,the majority of loans are small(less than$40,000),and almost all loans have a maturity of three years or less.9 originate(or purchase)in each county and year.In additio

100、n to this flow data from the CRA reports,we also collect stock data of outstanding SBL from the Call Reports,which are filed on a quarterly basis by each bank with the federal regulators.Information on SBL originated by traditional banks is used to compute measures of SBL concentration at the county

101、 level.Traditional small business credit(business credit cards)data We use comparable business loan data(through credit cards)from the Federal Reserves Y-14M reports.These data are reported monthly by bank holding companies with over$50 billion in assets.We use a 1 percent random sample of all busin

102、ess credit card accounts reported in the Y-14M data set.From this data set,we focus on those business card accounts that were open during the period 20162019 to match the small business loan data from Funding Circle and LendingClub.11 For the most part,the Y-14M reports contain similar data on borro

103、wers and other risk characteristics as those reported in the Funding Circle and LendingClub database(eg,origination date,origination amount,location of the borrowers,and borrowers credit scores).We use data on business credit card loans from the Y-14M reports to compare with SBL originated by Fundin

104、g Circle and LendingClub.We start with 548,808 business card accounts.After screening out those charge cards(no credit limit)and those with missing business owners FICO scores,we are left with 453,385 accounts.We then drop those business card accounts that were opened with missing APR data or with a

105、 promotional rate of 0 percent APR.Our final sample includes 275,024 business card accounts that were open during the period 20162019 that have data on business owners FICO scores and interest rate in APR.12 Zip code(or county)-level economic factors From the FDIC Summary of Deposits,we collect data

106、 on banking activity and the number of bank branches in each local community where fintech loans are made.Other general economic factors such as bankruptcy filings by businesses,market competition,house price indices,unemployment,etc.are collected from Haver Analytics,CoreLogic database,and other so

107、urces.We collect income data from the American Community Survey(ACS)U.S.Census Bureau(five-year estimates).We then match the associated economic factors by the loans zip code or at the county level(using the most granular level of data that is available).We have the house price index(HPI),unemployme

108、nt rate,business bankruptcy filings,and degree of bank competition and market concentration at the county level,and we have median income of residents and population at the zip code level.The Herfindahl-Hirschman index(HHI)of market concentration is calculated in two different ways,based on the shar

109、es of banks in SBL and in total bank deposits in a county.For the HHI based on SBL share,the data on the share of SBL by each bank in a county come from the CRA reports for banks that submit CRA reports;and from Call Reports(in conjunction with FDIC Summary of Deposits reports)for small community ba

110、nks that 11 We note that these data are constrained by the limited number of reporters and,as such,may not represent the entire population of firms that issue business credit cards.However,Y-14M reporters do represent over 80 percent of all credit cards issued by commercial banks.12 The final sample

111、 from Y-14M reports includes 65,158 business card accounts originated in 2016,64,538 in 2017,67,340 accounts in 2018,and 77,988 accounts in 2019.10 do not submit the CRA reports.Specifically,we apply the share of deposit-taking activities by each bank in each county to the amount of SBL from the ban

112、ks Call Reports for non-CRA reporters.In addition to measuring market competition using the HHI based on SBL activities(by banks)in a county,we also measure the number of bank branches per capita and changes in bank branches at the zip code level.We estimate the number of bank branches per capita(pe

113、r 100,000 people)using branching data from the FDIC Summary of Deposits reports and using population data(five-year estimates)from ACS as reported in 2018.Table 1 summarizes the descriptive statistics of the variables used in the regressions.The database covers the period 20162019.The first panel su

114、mmarizes the variables used in the regression that analyzes credit access.This is based on year and county or zip code level data,resulting in 9,688 observations.The Funding Circle SBL share is the ratio of its own SBL originated in each zip code in each year relative to the overall SBL that Funding

115、 Circle originated in all zip codes in each year.This share has an average of 0.04 and a maximum of 0.58,indicating that its loans are spread across a large number of zip codes although the loan may be quite concentrated in some specific areas in some years.Local economic factors include the unemplo

116、yment rate at the county level,the HPI at county level,business bankruptcy filing at county level,and median income at the zip code level.Local economic conditions are quite heterogeneous across counties or zip codes.For example,unemployment ranges from 1.6 percent to 19 percent,while median income

117、ranges from nearly$9,000 to more than$243,000.As for the measure of SBL market concentration,we consider the HHI at the county level,based on SBL by banks in each county in each year.Even in this case,conditions are quite different across counties.In addition,we use market competition measures at th

118、e zip code level based on banking service activities:1)the number of bank branches per capita in each zip code;2)changes in the number of bank branches in each ZIP code from the previous year to the current year;3)percent changes in the number of bank branches in each zip code from the previous year

119、 to the current year;and 4)a dummy indicator of whether the number of bank branches per capital in the zip code has declined from the previous year to the current year.The second panel of Table 1 describes summary statistics for the variables used in our simple horse race models(described in the nex

120、t section)that compare the FICO,VantageScore,and Funding Circle internal risk rating score(FC risk scores).This is based on loan-level data,resulting in 15,050 observations.The FC risk score is assigned using the companys proprietary model.We use dummy indicators for each loan considering the five c

121、ategories,from A+-rated(lowest risk)to D-rated(highest risk).Additional information on loan contract maturity by Funding Circle risk bands is reported in Table A1 in the Appendix.We define loans as being delinquent as of 24 months(or 12 months)after origination,if the borrower has a late payment(60+

122、days past due),as of 24 months(or 12 months)after origination,and zero otherwise.11 Descriptive Statistics Funding Circle Sample includes loan-level data from Funding Circle SBL platform for the period 20162019 Table 1 N Mean St.Dev.Min Max Credit Access Analysis Funding Circle SBL share1 9,688 0.04

123、 0.04 0.00 0.58 County unemployment(%)9,688 3.96 1.07 1.61 18.80 County HPI(in 00s)9,688 1.96 0.51 0.89 3.91 County business bankruptcy filings per capita 9,688 0.0001 0.0001 0.0000 0.0006 Zip Median income(in$100,000s)9,688 0.82 0.33 0.09 2.43 HHI:SBL concentration(in 000s)9,688 0.82 0.53 0.29 6.87

124、 Population(%)9,688 0.04 0.03 0.00 0.25 Dummy,decrease in branches 9,688 0.22 0.41 0.00 1.00 Percentage decrease in branches 9,688-0.03 0.07-0.75 0.00 Percent change in branches 9,688-0.02 0.10-0.75 2.00 No new firms(000s)9,688 2.51 4.09 1.27 20.17 County share of population above 65 9,179 15.36 3.8

125、7 7.42 41.24 Defaults as predicted by FICO,VantageScore,FC risk grade 12-month delinquency rate 15,040 0.04 0.19 0 1 24-month delinquency rate 15,040 0.07 0.25 0 1 FICO at origination 15,040 717 45 604 843 VantageScore 15,030 698 56 492 836 FC rating A 15,040 0.31 0.46 0 1 FC rating B 15,040 0.29 0.

126、45 0 1 FC rating C 15,040 0.14 0.35 0 1 FC rating D 15,040 0.05 0.21 0 1 APR residuals 13,392 0.00 0.01 0.07 0.19 Default probability as of 24 months after origination Delinquent loan dummy2 11,640 0.07 0.26 0.00 1.00 Acquisition score 11,640 6332 13856 100 99900 FICO at origination 11,640 715 45 60

127、4 843 VantageScore at origination 11,635 697 56 492 836 FC rating A 11,640 0.31 0.46 0.00 1.00 FC rating B 11,640 0.28 0.45 0.00 1.00 FC rating C 11,640 0.14 0.35 0.00 1.00 FC rating D 11,640 0.05 0.21 0.00 1.00 Ln(profit)11,640 10.81 1.34 1.39 15.16 Ln(gross revenue)11,640 13.59 1.09 9.87 18.09 Ln(

128、loan amount)11,640 11.53 0.79 10.13 13.12 Loan maturity in months 11,640 47.11 14.72 6.00 60.00 County unemployment 11,640 3.62 0.95 1.56 16.98 County HPI 11,640 209 54 98 391 County business bankruptcy filings per capita 11,640 0.00008 0.00005 0.00000 0.00150 1 Ratio of SBL loans originated(by Fund

129、ing Circle SBL platform)in zip code i in year t relative to total SBL loans(in all zip codes)originated in year t.2 Takes the value1 if the loan becomes delinquent(60+DPD)as of 24 months after origination;and zero otherwise.Sources:Funding Circle,CRA data,FDIC Summary of Deposits,Call Reports,Haver

130、Analytics,and US Census.12 The third panel of Table 1 includes the variables used in the regressions that model(in an exhaustive way)the probability of default on a loan.Here,we match loan-level data with various control factors including economic factors in the zip code where the loan is located,re

131、sulting in 11,640 observations.These models include not only the three different ratings on the borrower(FICO,Vantage,and FC risk scores)but also the business risk score from Experian,the so-called Acquisition Score.13 Moreover,the models include local economic conditions,loan characteristics(eg,loa

132、n amount,loan maturity in months,loan APR,and year of origination)and borrower characteristics(such as business profits and business revenue).The pairwise correlations between Funding Circle loan characteristics and economic factors are presented in Table A2 in the Appendix.Some stylized facts Fundi

133、ng Circle SBL activity increased in the period under investigation(see Figure 1).The data contain loans originated from 2016 to mid-2019;thus,the volume looks smaller in the last histogram rather than 2018 because it considers only six months(see left-hand panel).Our sample includes a total of 15,02

134、7 loans(about$2 billion total;see right-hand panel).The amount of SBL originated by Funding Circle in this period is quite remarkable,also considering other relevant platforms operating in the US.For example,in the period 20152018,the total of SBL originated by LendingClub was only$540 million.13 Di

135、fferent lenders may have different products and attributes from vendors such as Experian and Dun&Bradstreet.Funding Circle uses the Experian Acquisition score(which is a rating for the business,rather than the small business owner).The scale looks different than other scores(such as FICO or Vantage

136、Score),with a score of 7200 being in the 91st percentile.Unlike Funding Circle,the variable that measures business risk score(on the LendingClub SBL platform)is called an IP Score.This is comparable with the typical range used for FICO and other risk scores(from 300 to 850).Separately,for the measur

137、e of business owners risk score,we have included the FICO scores and Vantage Score for business owners as of the loan application date.Funding Circle SBL Activity(2016 to mid-2019)Figure 1 Loan$Amount and Number of Accounts Cumulative Amount Lent and Number of Accounts USD mn Number USD mn Number So

138、urce:Funding Circle.13 The average loan originated by Funding Circle in the period under analysis is around$134,000,with a minimum of$25,000 and a maximum of$500,000.Just as a comparison,the average loan originated by LendingClub is about half this value,or around$56,000,with a minimum of$2,000 and

139、a maximum of$600,000.Funding Circle loans are directed to firms with an average number of 12 employees and gross revenues of$1.5 million(compared with 11.6 employees and$1.1 million for LendingClub).From the top panel of Figure 2,the FICO scores of the business owners range from 600 to 850 in each y

140、ear,with a significant number of loans originated to below-prime business owners(red and blue in the upper-left panel,with a FICO score below 680).About half of the loans are associated with interest rates below 15 percent APR(green and orange in the upper-right panel).The bottom panels of Figure 2

141、show that the originated loan size ranges from$25,000 to$500,000(bottom-left panel),with maturity ranging from one year to five years.About half of the loans in each rating grade are longer-term loans with a five-year maturity(bottom-right panel).Funding Circle Loan Distribution:by FICO,APR,Amount,M

142、aturity Number of Loans Figure 2 Borrowers FICO Score by Origination Year Borrowers APR by Origination Year Funding Amount by Origination Year Loan Maturity Distribution Source:Funding Circle.14 Figure 3 shows that the top five states where loan are originated are the most populous:California(CA),Ne

143、w York(NY),Florida(FL),Texas(TX),and Illinois(IL),although these add to less than half of all the loan originations by Funding Circle(upper left-hand panel).14 In the remaining panels of Figure 3,it is notable that there is heterogeneity in firm profitability,firm size(as measured by revenue),and lo

144、an maturity for each level of risk rating(A+to D)assigned by Funding Circle.14 The full geographical distribution of SBL lending activity by state is reported in Figure A1 of the Appendix.The distribution is not too different from that of LendingClub(see Figure A2 in the Appendix).Just under half of

145、 LendingClub loans are to small businesses in the same five(most popular)states,but in a slightly different order:California,Florida,Texas,New York,and Illinois.Funding Circle Loan Distribution:by States;Profits,Revenue,and Maturity Across Credit Ratings Number of Loans Figure 3 Top 5 States by Orig

146、ination Year Borrowers Profit by Funding Circle Risk Rating Borrowers Revenue by Funding Circle Risk Rating Loan Maturity Distribution by Funding Circle Risk Rating Source:Funding Circle.15 Funding Circles own risk ratings are functionally comparable to FICO and VantageScores,but even prima facie,th

147、ey exhibit notable differences.Figure 4 compares the distribution of FICO scores,VantageScore,and Funding Circles own ratings.The plots show that the mode(median)score is 710(715)for FICO,650(693)for VantageScore;and A-rated for Funding Circle risk bands.About half of the loans received top ratings(

148、A or A+)from Funding Circle,although they may not be highly rated based on the traditional credit scoring systems.Figure 5 shows that a significant number of loans that would traditionally be considered below prime,based on FICO score and VantageScore(red and blue histograms),are assigned much bette

149、r ratings(A or A+)by Funding Circle.Indeed,as shown in Figure A3 in the appendix,the correlation between the rating grades assigned by Funding Circle and the traditional credit ratings assigned by FICO or Vantage Score have been almost always below 50 percent over the sample.15 Notably,this correlat

150、ion is even lower when LendingClub credit rating is compared with FICO and Vantage Score.As shown in Figure A3 in the Appendix,the correlation between the loan ratings assigned by LendingClub and the traditional scores is around 30 percent.15 This suggests that at least half of the variation in FC r

151、ating grades cannot be explained by traditional credit information that is incorporated in the FICO or VantageScore.The correlation is slightly higher for VantageScore than for FICO,probably because Vantage scores tend to account for some nontraditional data,such as utility and rent payments.Loan Di

152、stribution by FICO,VantageScores,and Funding Circles Rating Grades Frequencies Figure 4 Distribution of FICO Scores Distribution of VantageScores Distribution of FC Risk Rating Additional statistics on the distribution of credit scores:FICO:median score=715;mean score=717;VantageScore:median score=6

153、93;mean score=698;Funding Circle:a total of 15,096 loans,the median rating(at 7,548 position)is A-rated.Source:Funding Circle.16 Funding Circle Loans:Credit Score Distribution by FC Rating Grades Number of Loans Figure 5 FICO Distribution by Funding Circle Risk Bands VantageScore Distribution by Fun

154、ding Circle Risk Bands Source:Funding Circle.The divergence between Funding Circle risk bands and traditional risk scores is not random.Indeed,as shown in Figure 6,it is even larger in U.S.counties with a higher unemployment rate.The scores also show prima facie differences in their predictive power

155、.Figure 7 presents delinquency rates for different combinations of Funding Circle risk ratings and the FICO or VantageScore ratings.This figure is divided into two panels:the left panel for FICO scores and the right panel for VantageScore.The size of the bubbles is proportional to the share of the f

156、irms in each rating distribution(ie,each combination of FC and FICO or VantageScore)based on the origination amount.On the vertical axis,the panel reports the delinquency rate(ie,the percentage of loans more than 60 days past due relative to the total number of loans).On the horizontal axis,it repor

157、ts the risk matrix with the Funding Circle credit rating compared with Risk Assessments Diverge More in Areas with Higher Unemployment Figure 6 1 Funding Circle risk grades have been mapped to FICO scores based on the min-max range of the latter.The values have then been de-meaned.Sources:Funding Ci

158、rcle,CRA data,FDIC Summary of Deposits,Call Reports,Haver Analytics.17 the traditional rating.As the FICO and VantageScore are continuous variables,we have segmented them into three different risk bands and then compared these with the five different Funding Circle risk ratings(D through A+).In the

159、left panel,for a given FICO risk band(ie,high risk),the expected loss rate is strictly monotonic with the Funding Circle credit ratings(ie,the patterns of the dots show that the Funding Circle risk bands rank orders for expected loss).Conversely,given an internal rating(ie,B,C,or D),the delinquency

160、rate is not strictly monotonic with the FICO score.For example,the dot associated with the D Funding Circle risk bands for the low-risk FICO band indicates a higher risk than the corresponding D rating in the medium-risk FICO band.Moreover,the Funding Circle risk bands have a narrow range of default

161、 for each rating grade:high-default rates for D-rated and low-default rates for A-rated.In contrast,the range of default rate is broader based on FICO or Vantage scores,ranging from delinquency rates of 1.7 percent to 21.4 percent for the low-risk FICO band.Most importantly,by using its proprietary

162、scoring model,Funding Circle has been able to make credit available to those high-risk borrowers(based on FICO scores).Table 2 presents a matrix of delinquency rate for loans in the various risk buckets,based on Funding Circle risk bands versus the traditional risk bands(FICO scores).The last column

163、 of Table 2 presents the portfolio share by FICO risk bands.As shown,12.6 percent of the portfolio of loans originated by Funding Circle would fall into the high-risk FICO cluster.Banks use a mix of FICO score information and soft information from loan officers,but in general,they would not lend to

164、these borrowers in the U.S.16 With its more granular scoring model,Funding Circle can offer credit and in turn help these borrowers gain access to the SBL market.16 Anecdotally,many U.S.banks use a cutoff and do not lend to borrowers with FICO credit scores below 580.Delinquency Rates Decline Signif

165、icantly for Higher FC Risk Bands,Controlling for FICO and VantageScore Bands In Percent Figure 7 Default Rate for FC Risk Band and FICO Default Rate for FC Risk Band and VantageScore This figure shows the delinquency rate(ie,the percentage of loans more than 60 days past due relative to the total nu

166、mber of loans).The plots are calculated based on a dummy that takes value 1 if the loan becomes delinquent(60+days-past-due)as of 24 months after origination and zero otherwise.The size of each bubble is proportional to the total origination amount.Source:Funding Circle.18 Table 3 reports the APR by

167、 Funding Circle rating grades and by FICO buckets.There is little variation of interest rates across Funding Circle risk grades.For example,for loans with Funding Circle D-rated,the associated APRs are almost the same regardless of their FICO scores,ranging from 31.0 percent APR for the low-risk FIC

168、O band to 31.3 percent APR for the high-risk FICO band.In contrast,we observe a wide variation of APR across FICO buckets.For example,for the high-risk FICO bucket,interest rates range from 11.5 percent APR to 31.3 percent APR.This characteristic is similar but less pronounced compared with the same

169、 distribution for LendingClub SBL platform(see Table A3 in the Appendix).These simple statistics indicate that the internal rating system of Funding Circle differentiates between borrowers more than the traditional credit ratings like FICO scores,thus allowing Funding Circle to extend loans to borro

170、wers who would otherwise be excluded from credit markets.However,two aspects remain to be assessed.First,we need to verify whether Funding Circle lending improves financial inclusion in underserved areas of the country.Second,we need to test whether the Funding Circle rating system based on ML techn

171、iques and big data outperform(ex Delinquency Rate by Funding Circle Rating Grades and FICO Scores Table 2 Funding Circle Risk Grades Total FICO Portfolio Share D C B A A+FICO Band Low Risk 21.4%11.3%5.1%3.3%1.7%3.6%36.3%Medium Risk 17.4%10.6%7.1%4.3%3.5%6.7%51.1%High Risk 21.1%13.3%10.5%7.6%6.0%11.8

172、%12.6%Total FC Risk Grade 19.3%11.5%7.3%4.3%2.6%6.5%Portfolio Share 3.1%12.3%27.5%33.8%23.3%Delinquency rates are defined as the share in the total number of outstanding loans 60 days or more past due,divided by the total number of loans.These are shown for different ranges of FICO scores and Fundin

173、g Circle risk bands,over the period 20162019.The(discrete)Funding Circle credit ratings at origination are divided into five different risk groups(A+through D),while the(continuous)scores of the FICO credit bureau are divided into three corresponding to risk level:Low Risk(FICO739);Medium Risk(FICO

174、between 670739);and High Risk(FICO739);Medium Risk(FICO between 670 and 739);and High Risk(FICO670).Source:Authors calculations based on data from Funding Circle.19 post)the more traditional rating/scoring in predicting defaults.We perform this analysis in the next section.4.Empirical analysis Credi

175、t access and financial inclusion In the first step of the empirical analysis,we want to assess where fintech SBL is more extensive,to shed light on its role to improve credit access and thus financial inclusion of previously underserved businesses and geographies.The estimation is specified as follo

176、ws:=+(1)where z,c,t stand for zip code,county,and time,respectively.Our dependent variable,is the ratio of SBL loans originated by the Funding Circle SBL platform in zip code z,in county c in year t relative to total SBL loans originated by Funding Circle in year t.To control for time-invariant stat

177、e characteristics(such as state-specific unemployment benefits,property taxation,or corporate rules),we include state fixed effects().17 The unemployment rate(),house price index(),and level of business bankruptcy filings in the last 24 months(BBF)are calculated at the county level,while the median

178、level of income()is at the zip code level.These variables capture economic factors that could influence the development of fintech SBL in a specific geographic location.The HHI measures the level of market concentration and is calculated as the sum of the squared share of SBL lending by each bank in

179、 each county.To control for demographic factors,we also include the percentage share of population in each zip code()as more loans are expected to be granted in an area with a larger population.The results are presented in Table 4.As a first-pass analysis,in the first column(Model 1)of Table 4,we co

180、rrelate the FC SBL ratio with a simple model that includes only the share.This model can explain 7.4 percent of the variability of the FC SBL ratio.In the second column(Model 2)of Table 4,we include the other(time varying)county/zip code characteristics.The unemployment rate in a county is positivel

181、y correlated with FCs lending share in that area.A one standard deviation increase in the unemployment ratio can be associated with an increase in the FC SBL share by 0.002 percentage points in a specific zip code(1.07*0.002).This is economically relevant as it represents 5 percent of Funding Circle

182、 credit in an average zip code.17 We do not include origination year fixed effects because we want to focus on whether loans go into more underserved areas overall rather than comparing within each origination year.We include origination year fixed effects in the analysis at the loan level.20 An inc

183、rease in house prices is positively correlated with the FC SBL share,but the effect is not statistically significant.This may reflect the fact that fintech SBL is not typically collateralized(see also Gambacorta et al.,2020).By contrast,the effect of the median income(calculated at the zip code leve

184、l)is positive and statistically significant,reflecting changes in demand conditions for firms that translate into higher demand for credit by firms.A one standard deviation increase in median income is associated with a rise in the FC SBL share by 0.004 percentage points(0.33*0.012).This is also eco

185、nomically relevant as it represents around 10 percent of Funding Circle credit in an average zip code.Interestingly,fintech SBL origination is positively associated with a higher rate of business bankruptcy filings(BBF),supporting our hypothesis that fintech SBL lenders could expand credit access to

186、 more small business owners(especially those with little Credit Access Analysis Table 4 Funding Circle SBL Share Model 1 Model 2 Model 3 Model 4 Model 5 Model 6 Model 7 County unemployment 0.00197*0.00199*0.00197*0.00197*0.00153*0.00196*(0.000422)(0.000423)(0.000422)(0.00042)(0.00040)(0.00044)County

187、 HPI(in 00s)0.000124 0.000142 0.000122 0.00011-0.00367*0.00027 (0.00132)(0.00132)(0.00132)(0.00132)(0.00139)(0.00141)County business bankruptcy 48.29*48.01*48.32*48.27*41.23*52.95*filings per capita (7.092)(7.070)(7.091)(7.09599)(7.16031)(7.75989)Median income(in 00,000s)0.0118*0.0118*0.0118*0.0118*

188、0.0118*0.0116*(0.00131)(0.00131)(0.00131)(0.00131)(0.00131)(0.00134)SBL concentration(in 000s)0.00106 0.00108 0.00105 0.00107 0.00179*0.00155 (0.000829)(0.000829)(0.000829)(0.00083)(0.00083)(0.00103)Population(%)0.289*0.293*0.290*0.292*0.292*0.288*0.281*(0.0170)(0.0180)(0.0181)(0.0180)(0.01802)(0.01

189、807)(0.01892)Dummy,decrease in branches 0.00209*(0.000963)Percentage decrease 0.00293 in branches (0.00465)Percent change in branches 0.00347 (0.00323)No new firms(000s)0.00081*(0.00015)County share of population -0.00026*above 65 (0.00012)Model OLS OLS OLS OLS OLS OLS OLS Observations 10,279 9,688

190、9,688 9,688 9688 9688 9179 R2 0.074 0.085 0.085 0.085 0.085 0.089 0.083*/*/*denotes results that are significant at the 1%/5%/10%levels,respectively.The sample is based on loan-level data from Funding Circle SBL Platform for the period:2016 Q12019 Q2.All regressions include constant and state-level

191、dummy indicators.Dependent variable is Funding Circle SBL Share,which is defined as the ratio of SBL loans originated(by Funding Circle SBL platform)in zip code i in year t relative to total SBL loans(in all zip codes)originated in year t.Sources:Funding Circle,CRA data,FDIC Summary of Deposits,Call

192、 Reports,Haver Analytics,and US Census.21 track record)through their use of alternative data.The effect is economically relevant.A one standard deviation increase in BBF is associated with a rise in the FC SBL share of 0.005 percentage points(0.0001*48.29).This represents around 12 percent of Fundin

193、g Circle credit in an average zip code.Market competition(based on the share of SBL lending by each bank in each county)does not affect the FC SBL ratio.18 The three columns(Models 3 to 5)of Table 4 control for changes in the structure of bank branches.In particular,the third column(Model 3)consider

194、s a dummy that takes the value of 1 for those counties that experienced a decrease in bank branches from the previous year,and zero elsewhere.We find that in these counties,the FC SBL share is significantly higher.However,the effect is positive but not statistically significant when considering the

195、percentage decrease in bank branches(Model 4)and the percent change in branches(Model 5).The last two columns of Table 4(Models 6 and 7)control for the number of new firms in a county,calculated as the change in the number of firms from year t to year t-1 plus the number of firm deaths in year t-1,a

196、nd the share of county population above 65 years of age.The results indicate that more new firms are associated with greater credit access(Model 6).This could result from these being areas with many firm entries and exits,and potentially to greater credit demand,all else equal.19 Finally,the results

197、 from model 7 suggest that there is less lending where there share of county population over 65 is higher.18 Similar results are obtained using the share of deposit-taking activities by each bank in each zip code for non-CRA reporters to estimate their SBL as a measure of market concentration(see Ta

198、ble A4 in the Appendix).19 The results are qualitatively similar when we control for the number of new firm establishments instead of the number of new firms.Economic Contribution of Factors in the Credit Access Analysis Table 5 Model 2 Model 3 Model 4 Model 5 Model 6 Model 7 Regressor Shapley Value

199、 Percent Shapley Value Percent Shapley Value Percent Shapley Value Percent Shapley Value Percent Shapley Value Percent Country unemployment 0.00353 4.17%0.00354 4.16%0.00353 4.17%0.00353 4.17%0.00293 3.31%0.00363 4.4%County HPI(in 00s)0.00365 4.31%0.00368 4.32%0.00364 4.30%0.00364 4.30%0.00298 3.37%

200、0.00396 4.79%County business bankruptcy filings per capita 0.00622 7.35%0.00617 7.25%0.00622 7.36%0.00621 7.34%0.00532 6.02%0.00628 7.6%Median income(in 00,000s)0.00792 9.37%0.00785 9.23%0.0079 9.34%0.0079 9.33%0.00782 8.83%0.00746 9.02%SBL concentration(in 000s)0.00033 0.39%0.00033 0.39%0.00033 0.3

201、9%0.00033 0.39%0.00035 0.4%0.00014 0.17%Population(%)0.04645 54.94%0.04596 54.03%0.04643 54.89%0.04643 54.85%0.04496 50.79%0.04233 51.23%Dummy,decrease in branches 0.00096 1.12%Percentage decrease in branches 0.00011 0.13%Per cent change in branches 0.00018 0.21%No new firms(000s)0.00981 11.08%Count

202、y share of population above 65 0.00279 3.37%State-level dummies 0.01645 19.46%0.01658 19.49%0.01642 19.41%0.01642 19.40%0.01434 16.2%0.01605 19.43%The economic contributions refer to the econometric models reported in Table 4.The sample includes loan-level data from Funding Circle SBL Platform for t

203、he period:20162019.Sources:Funding Circle,CRA data,FDIC Summary of Deposits,Call Reports,Haver Analytics,and US Census.22 In Table 5,we show the Shapley value decomposition of the statistical contribution to explain the FC SBL share.This indicates that the population share and state fixed effects ca

204、pture,respectively 55 percent and 19 percent of the FC SBL share variability.Median income at the zip code level explains 9 percent,while unemployment and bankruptcy filings explain a total of 12 percent,taken together.These last two variables represent a good proxy for the overall contribution of f

205、inancial inclusion factors that can be associated with FC SBL share.Ex-post default performance As a second step of the analysis,we assess whether the Funding Circle rating system based on ML techniques and big data outperforms(ex post)the more traditional rating scoring in predicting defaults.First

206、,we compare the performance of the Funding Circle credit scoring model versus traditional FICO and Vantage scores.Specifically,our goal is to assess whether the fintech credit scoring model(based on ML plus big data)is better able to predict borrowers defaults than traditional credit scoring models.

207、The analysis is performed at the(more granular)loan level.We start by estimating the following model to predict defaults:(,)=,+,(2)where(,)indicates the probability for the loan not to be repaid(and to generate a loss).The credit scoring refers to borrower i at time t.We consider one at the time the

208、 FICO score,the VantageScore,and the Funding Circle risk grades.The FICO and Vantage scores are continuous variables,while the Funding Circle rating grade is organized into buckets.The model includes state()and time origination()fixed effects.The results are presented in the first three columns of T

209、able 6.Panel(a)considers delinquency as of 12 months from origination,while Panel(b)analyzes the effects as of 24 months after origination.All estimates use a Logit regression model.Credit scores are always a highly significant predictor of delinquency.However,the pseudo R2 of the model that uses FC

210、 risk grades(column 3)is significantly higher than that obtained using the FICO score(column 1)and the VantageScore(column 2).The results are similar for both considering a 12-month and 24-month delinquency horizon.Results are also consistent when adding APR residuals(see final column and below).Tab

211、le 7 compares the performance of the three different credit scoring approaches.The table is divided into two panels,with two different delinquency rate horizons(12 months and 24 months after origination).Each panel reports the area under the receiver operating characteristics curve(AUROC)for every c

212、redit scoring method.The AUROC is a widely used metric for judging the explanatory power of credit scores.The AUROC ranges from 50 percent(purely random prediction)to 100 percent(perfect prediction).The formal test on the difference in performance across the models can be done comparing the 95 perce

213、nt confidence interval reported in the last two columns of Table 7,with significant improvement in predictive ability when moving from either FICO or Vantage scores to Funding Circle rating grades.23 PD as Predicted by FICO,VantageScore,and Funding Circle Risk Grades Table 6 Panel A:12-Month Delinqu

214、ency Rates (1)(2)(3)(4)FICO Score-0.00943*(0.00101)VantageScore -0.00706*(0.000795)FC Risk Grades A 0.575*0.573*(0.182)(0.194)B 1.188*1.235*(0.172)(0.182)C 1.830*1.837*(0.175)(0.186)D 2.361*2.392*(0.191)(0.200)APR residuals 2.957 (4.639)Observations 15,017 15,007 15,017 13,337 Pseudo R2 0.0689 0.067

215、0 0.104 0.109 Panel B:24-Month Delinquency Rates (I)(II)(III)(IV)FICO Score-0.0104*(0.000809)VantageScore -0.00774*(0.000638)FC Risk Grades A 0.601*0.622*(0.134)(0.143)B 1.178*1.227*(0.127)(0.137)C 1.748*1.736*(0.133)(0.143)D 2.271*2.279*(0.150)(0.159)APR residuals 2.862 (3.688)Observations 14,961 1

216、4,951 14,961 13,281 Pseudo R2 0.0916 0.0889 0.118 0.118 The table reports the estimates for a logit regression analysis.All regressions include state dummies and origination year dummies.Source:Funding Circle 24 Figure 8 shows the receiver operating characteristics(ROC)curve for each credit scoring.

217、The ROC curve is created by plotting the true positive rate(TPR)against the false positive rate(FPR)at various threshold settings.The TPR is also known as sensitivity.The FPR is also known as the fall-out or probability of false alarm and can be calculated as(1 specificity).The left-hand panel of Fi

218、gure 8 reports the results for the three different credit scores searching for unpaid loans as of 12 months after origination,while the right-hand panel repeats the analysis for a 24-month performance window after Area Under the Receiver Operating Characteristic(ROC)Curves Table 7 Panel A:ROC Curves

219、 12-Month Delinquency Rates Observations AUROC Std.Err.95%Confidence Interval FICO Score 13,337 0.7176 0.0107 0.6967 0.73853 VantageScore 13,337 0.7136 0.0109 0.69228 0.73487 FC Risk Grades 13,337 0.7645 0.0102 0.74455 0.7844 FC Risk Grades and APR Residuals 13,337 0.7676 0.0101 0.74778 0.78733 Pane

220、l B:ROC Curves 24-Month Delinquency Rates Observations AUROC Std.Err.95%Confidence Interval FICO Score 13,281 0.7312 0.0084 0.71482 0.74764 VantageScore 13,281 0.7243 0.0084 0.70783 0.74086 FC Risk Grades 13,281 0.7643 0.0079 0.74883 0.77981 FC Risk Grades and APR Residuals 13,281 0.7665 0.0079 0.75

221、102 0.78206 The table reports the estimates for the logit regression,which include state-and origination year-level dummies,as reported in Table 6.Source:Funding Circle.Predictive Power of FICO,VantageScore,and Funding Circle Risk Grades Figure 8 ROC Curve 12-Month Delinquency Rates ROC Curve 24-Mon

222、th Delinquency Rates The x-axes show the fraction of false positives,whereas the y-axes show the fraction of true positives.The higher the curve the stronger the performance of the model.Based on the models in Table 6.Source:Funding Circle.25 origination.In both cases,the results show that the Fundi

223、ng Circle risk grades perform better than the other two rating approaches.The difference between the FICO and the Vantage scores is marginal,with the first one performing slightly better.The three models are statistically different at the 5 percent level,as formally verified by inspection of the las

224、t two columns of Table 7.We conduct four additional tests with a view of shedding further light on the informational advantage of the FC rating grades.First,as the FICO and the Vantage scores are continuous variables while the FC rating grade is expressed in dummies,we have rerun all the results usi

225、ng similar risk buckets for all three approaches.We divide the FICO score and the VantageScore into five different buckets,to be comparable with the FC rating grades A to D.The results,reported in Figure A5(in the Appendix),indicate that the FC rating grade has always a greater explanatory power tha

226、n the FICO score and the Vantage score.Second,we perform a similar test by adding to the model the information content of the interest rates.If interest rates are simply assigned based on the credit scores,they should add no additional information.However,it is possible that in some cases interest r

227、ates may be assigned based on additional pieces of information other than the credit ratings.We find that the APR is closely linked to the Funding Circle risk band(see the left-hand panel of Figure A6 in the Appendix),but there is still some residual variability.For this reason,we have included in t

228、he last column of Table 6 a regression that includes the residual of a regression of the interest rate on FC rating grades.The test aims to control for the fact that the interest rate could contain additional information that is not already included in Funding Circle rating grades.The coefficient on

229、 the APR residual in last column of Table 6 is not statistically significant and the AUROC improves just marginally(see that last row of Panel A and B of Table 7).This indicates that adjustments to APRs are not systemically in one direction(to riskier or less risky borrowers)and/or that all relevant

230、 information available to Funding Circle is already included in the FC rating grade.Third,to assess how the improvement in predictive power varies by geography,we compare the improvement in the AUROC of the FC rating grade in areas with unemployment that is above the median with areas where it is at

231、 or below the median.Table 8 shows that the improvement in the AUROC is 7.5 percentage points in high-unemployment areas,versus only 2.4 percentage points in low-unemployment areas,over a 12-month horizon.This complements our results on credit access,showing that the FC risk bands outperform traditi

232、onal scores especially in underserved areas.Improvement in Receiver Operating Characteristic(ROC)Curves Table 8 Increase in AUROC(FICO Vs FC risk grades)Unemployment above median Unemployment at or below median Without unemployment breakdown 12-Month Delinquency Rates 7.46%2.36%4.69%24-Month Delinqu

233、ency Rates 4.74%2.11%3.31%The table reports the increase in the area under the ROC curve(AUROC)for the logit regression,which include state-and origination year-level dummies,as reported in Table 6.Source:Funding Circle.26 Fourth,we consider how much the Funding Circle rating grade adds to a complet

234、e model that includes the FICO score,the VantageScore and a set of further traditional variables.The rationale of this test is to verify the contribution of Funding Circles own rating above and beyond what could be captured by traditional credit ratings.Table 9 presents the analysis of default proba

235、bility as of 24 months after Default Probability as of 24 Months After Origination Table 9 Delinquent Loan Dummy as of 24 Months After Origination (1)(2)(3)Acquisition score-0.00001*-0.00001*-0.00001*(0.000005)(0.000004)(0.000004)FICO at origination-0.00727*-0.00526*(0.00121)(0.00124)VantageScore-0.

236、00418*-0.000370 (0.000970)(0.00101)FC rating A 0.609*0.494*(0.150)(0.152)FC rating B 1.245*1.044*(0.143)(0.152)FC rating C 1.852*1.589*(0.151)(0.164)FC rating D 2.497*2.165*(0.173)(0.189)Ln(profit)-0.0460-0.0216-0.0300 (0.0306)(0.0317)(0.0318)Ln(gross revenue)-0.217*-0.214*-0.201*(0.0525)(0.0528)(0.

237、0533)Ln(loan amount)0.547*0.572*0.606*(0.0734)(0.0760)(0.0771)Loan maturity in months 0.00402 0.00537*0.00466 (0.00299)(0.00307)(0.00310)Unemployment 0.0493 0.0207 0.0235 (0.0377)(0.0388)(0.0388)County HPI 0.00177 0.000936 0.00121 (0.00125)(0.00128)(0.00129)County business bankruptcy -1,358*-1,551*-

238、1,487*filings per capita (798.9)(802.2)(808.4)Observations 11,580 11,585 11,580 Pseudo R2 0.110 0.140 0.144*/*/*denotes results that are significant at the 1%/5%/10%levels,respectively.The table reports the estimates for a logit regression which include a constant,state dummies,and origination-year

239、dummy indicators.The sample includes loan-level data from Funding Circle SBL platform for the period:20162019.Dependent variable is a binary variable that takes the value of 1 if the loan becomes delinquent(60+DPD)as of 24 months after origination and zero otherwise.Sources:Funding Circle,CRA data,F

240、DIC Summary of Deposits,Call Reports,and Haver Analytics.27 origination.20 The first column reports the result including the FICO,the VantageScore and a set of traditional variables.The second column reports the results including the Funding Circle rating grade and the same set of the traditional va

241、riables.In both columns,we also include the Acquisition score that is assigned to the specific business,rather than the small business owner.Interestingly,moving from the first column to the second column,the R2 increases by 3 percentage points,from 11.0 percent to 14.0 percent.In the final column,w

242、e consider a model with all the credit scoring approaches and the set of traditional variables,and the R2 increases further to 14.4 percent.By comparing the R2 in the first and the third column,we can infer that the Funding Circle rating grade explains almost one third of the delinquency behavior in

243、 this more saturated model.To wrap up,Figure 9 shows a comparison between small business loans originated by the two fintech lenders and the traditional credit source through credit cards issued by large banks(data at account level from Y-14M).There is evidence supporting our earlier findings that f

244、intech lenders have the potential to move toward a more inclusive financial system where small business owners who are considered below prime could get access to business funding and could do so at a lower cost than otherwise.Panel A of Figure 9 compares FICO distribution for loans that were origina

245、ted in 20162019.It is interesting to note that borrowers who chose fintech lenders include those with relatively high FICO scores as well as those below-prime business owners.About half of fintech lenders SBL portfolios,from Funding Circle and LendingClub,are small business loans made to business ow

246、ners with FICO scores 700 or higher.However,this is still a much smaller portion compared with bank loans.About 80 percent of bank business cards were issued to business owners with FICO scores above 700,and more than half of all business card holders have FICO scores above 750.Panel B of Figure 9 c

247、ompares the funding costs faced by business owners when borrowing from the specific fintech lenders in our sample vs.through small business credit cards.About 50 percent of small business loans originated by Funding Circle in each year have an APR below 15 percent and a substantial share of borrower

248、s with FICO below 675 also received loans from Funding Circle with an APR below 15 percent.21 For LendingClub,a substantial share of borrowers with FICO below 675 received an APR below 20 percent.For bank business cards(Y-14M data),only a small portion of business cards were issued to business owner

249、s with FICO scores below 675,and the(contractual)interest rates charged to these business owners were mostly above 20 percent APR.20 We also find consistent results when we observe delinquency within a shorter window of 12 months after origination.The test is reported in Table A5 of the Appendix.21

250、As mentioned earlier,not all fintech lenders are the same.These findings based on Funding Circle and LendingClub may not be applicable to other fintech SBL platforms.28 Comparing Interest Rates on SBL Originated by Fintech Lenders vs.Traditional Banks(Controlling for Business Owners Credit Scores)Fi

251、gure 9 Panel A:FICO Distribution by Origination Year(20162019)Funding Circle SBL Lending Club SBL Banks(Business Cards)Borrowers from fintech lenders include those with relatively high FICO scores and those below prime.Many creditworthy SBL owners also choose to take out loans from fintech lenders.A

252、bout half of fintech lenders SBL portfolios,from Funding Circle and LendingClub,are small business loans made to business owners with FICO scores of 700 or higher.In contrast,about 80 percent of bank business cards were issued to business owners with FICO score above 700,and more than half of all bu

253、siness card holders have FICO above 750.Sources:Funding Circle,LendingClub,and Y-14M.Panel B:APR Distribution by Business Owners FICO Scores and Origination Year Funding Circle SBL Lending Club SBL Banks(Business Cards)About 50 percent of small business loans originated by Funding Circle in each yea

254、r have an APR below 15 percent(not shown here)and a significant amount of SBL with FICO below 675 also received an APR below 15 percent.For LendingClub,a significant amount of SBL with FICO below 675 received an APR below 20 percent.For bank business cards(Y-14M data),a small portion of business car

255、ds were issued to business owners with FICO below 675,and the(contractual)interest rates charged to these business owners were mostly above a 20 percent APR.Sources:Funding Circle,LendingClub,and Y-14M.5.Conclusions Our analysis,based on a unique proprietary data set of two large fintech SBL platfor

256、ms and additional proprietary data on comparable bank lending over the period 20162019,supports the hypothesis that fintech lenders have been able to expand credit access to those underserved small business owners who are not likely to receive funding from traditional lenders.This may be particularl

257、y relevant for those 29 small business owners with a short credit history and those in areas that face a higher local unemployment rate and a higher rate of business bankruptcy filing.We indeed find that Funding Circle lent to many small business firms that,because of the owners FICO score,would not

258、 have had access to bank loans,and that it lent more in areas with higher unemployment and business bankruptcies,controlling for other risk characteristics.Our results also suggest that alternative data about the small businesses and their owners can play an important role in allowing fintech SBL pl

259、atforms to expand credit access.We find that the ratings that Funding Circle assigns to each loan were important in explaining the future credit performance of the loans over the 24-month period after loan origination.The information used by Funding Circle(in its process to risk rank each loan)is su

260、perior to the information content of traditional credit risk measures such as the FICO and Vantage scores.The contribution of these alternative data increased further in areas with a high unemployment rate.In a saturated model that includes the business credit rating by rating agencies(ie;the busine

261、ss owners credit rating by FICO or Vantage scores),the general characteristics of the loan terms(maturity,origination date,loan amount),and the local economic conditions where the businesses are located,our results indicate that Funding Circles credit rating contributes significantly and explains ab

262、out one-third of the variation in a loans default probability.This finding is consistent with previous studies for fintech personal lending,and it provides support for the use of alternative data in small business lending as well.These findings have relevance for the role of fintech lenders going fo

263、rward.Outside our period of analysis,fintech lenders also played a role in facilitating loans to small mom-and-pop shops that did not have established banking relationship during the COVID-19 pandemic,which began in February/March 2020.When funding supply mostly dried up during the lockdown,most fin

264、tech SBL lenders refocused their loan originations toward the U.S.PPP loans,and many partnered with banks.While most banks had to prioritize their existing business customers in processing PPP loan applications,leaving smaller businesses exposed to bankruptcy risk,fintech lenders entered the space t

265、o fill the credit gap.Fintech partnerships with community banks during the pandemic made it possible for partnered banks to reach new customers,allowing small banks as a group to originate a larger share of PPP loans than their share of banking assets.22 While offering similar loan products as banks

266、,fintech lenders have been subject to a different set of regulations.All consumer loans from banks and nonbanks are generally subject to some consumer protection laws,but nonbank lenders are not subject to the periodic onsite examinations to which the banks are subject.However,through recent partner

267、ships with banks,some fintech platforms have also been subject to examination(as a significant banking service provider)or are indirectly subject to the rigorous standards that banks must comply.Several fintech platforms have recently become a bank either through acquisition or being granted a banki

268、ng charter,allowing them to access low-cost funding through insured deposits.Banks have also been investing and partnering with fintech vendors to access todays technology.Bank loans and fintech loans are likely to become more alike as this trend continues.It is important to remember that fintech le

269、nders are not all the same;thus,the results found in this paper may not necessarily apply to other fintech SBL platforms.22 As an example,about 65 percent of PPP loans that were originated by Funding Circle during the pandemic were new customers with no prior business relationship.30 Most important,

270、we have demonstrated the potential of what the fintech platforms and their use of alternative data could do to move us toward a more inclusive financial system.As collaboration and partnerships grow among traditional banks and fintech firms,they would become more efficient in utilizing borrowers dat

271、a using todays technology and likely to work together in enhancing financial inclusion and the overall economic performance.References Allen,F.,X.Gu,and J.Jagtiani(2022).“Fintech,Cryptocurrencies,and CBDC:Financial Structural Transformation in China.”Journal of International Money and Finance,forthc

272、oming.Allen,F.,X.Gu,and J.Jagtiani(2021).“A Survey of Fintech Research and Policy Discussion.”Review of Corporate Finance 1:259339.Allen,F.,I.Goldstein,and J.Jagtiani(2018).“The Interplay Among Financial Regulations,Resilience and Growth.”Journal of Financial Services Research 53,June,141162.Atkins,

273、R.,L.Cook,and R.Seamans(2021)“Discrimination in Lending?Evidence from the Paycheck Protection Program.”NBER Working Paper,May 31.Bates,T.,and A.Robb(2015).“Impacts of Owner Race and Geographic Context on Access to Small-Business Financing.”Economic Development Quarterly 30(2),159x170.Beck,T.,and A.D

274、emirg-Kunt(2006).“Small and Medium-Size Enterprises:Access to Finance as a Growth Constraint,”Journal of Banking and Finance 30(11):29312943.Bellucci,A.,A.Borisov,and A.Zazzaro(2010).“Does Gender Matter in BankFirm Relationships?Evidence from Small Business Lending.”Journal of Banking and Finance 34

275、(12),29682984.Berg,T.,V.Burg,A.Gombovi,and M.Puri(2020).“On the Rise of Fintechs Credit Scoring Using Digital Footprints.”Review of Financial Studies 33,28452897.Berger,A.N.,and W.S.Frame(2007).“Small Business Credit Scoring and Credit Availability,”Journal of Small Business Management 45(1),522.Ber

276、ger,A.N.,A.M.Cowan,and W.S.Frame(2011).“The Surprising Use of Credit Scoring in Small Business Lending by Community Banks and the Attendant Effects on Credit Availability,Risk and Profitability.”Journal of Financial Services Research 39(1-2),117.Buchak,G.,G.Matvos,T.Piskorski,and A.Seru(2018).“Finte

277、ch,Regulatory Arbitrage and the Rise of Shadow Banks.”Review of Financial Studies 33,28452897.Carter,S.,E.Shaw,W.Lam,and F.Wilson(2007).“Gender,Entrepreneurship and Bank Lending:The Criteria and Processes Used by Bank Loan Officers in Assessing Applications,”Entrepreneurship Theory and Practice,31(3

278、),427444.Cole,R.,and T.Sokolyk(2016).“Who Needs Credit and Who Gets Credit?Evidence from the Surveys of Small Business Finances.”Journal of Financial Stability 24,4060.Cornelli,G.,V.Davidson,J.Frost,L.Gambacorta,and K.Oishi(2019).“SME Finance in Asia:Recent Trends in Fintech Credit,Trade Finance and

279、 Beyond,”in M.Amstad,B.31 Huang,P.Morgan,and S.Shirai(eds.),Central Bank Digital Currency and Fintech in Asia,Tokyo:Asian Development Bank Institute.Cornelli,G.,J.Frost,L.Gambacorta,R.Rau,R.Wardrop,and T.Ziegler(2020).“Fintech and Big Tech Credit:A New Database.”BIS Working Paper 887(September).De R

280、oure,C.,L.Pelizzon,and P.Tasca(2016).“How Does P2P Lending Fit into the Consumer Credit Market?”Deutsche Bundesbank Discussion Papers,30.Dice,C.A.,and J.Liebersohn(2020).“Does Fintech Substitute for Banks?Evidence from the Paycheck Protection Program.”Ohio State and University of California,Irvine R

281、esearch Working Paper.Dolson,E.,and J.Jagtiani(2021).“Which Lenders Are More Likely to Reach Out to Underserved Consumers:Banks versus Fintechs versus Other Nonbanks?”Federal Reserve Bank of Philadelphia Working Paper 21-17(April).Erel,I.,and J.Liebersohn(2021).“Can FinTech Reduce Disparities in Acc

282、ess to Finance?Evidence from the Paycheck Protection Program?”NBER Working Paper(September).Financial Stability Board(2017).“Financial Stability Implications from Fintech,”FSB Report,June 27,2017,http:/www.fsb.org/wp-content/uploads/R270617.pdf.Financial Stability Board(2019).“Evaluation of the Effe

283、cts of Financial Regulatory Reforms on Small and Medium-Sized Enterprise(SME)Financing Consultative Document”(June).Frame,W.S.,A.Srinivasan,and L.Woosley(2001).“The Effect of Credit Scoring on Small-Business Lending.”Journal of Money,Credit and Banking 33(3),813.Frost,J.,L.Gambacorta,Y.Huang,H.Shin,

284、and P.Zbinden(2019).“BigTech and the Changing Structure of Financial Intermediation.”Economic Policy 34(100):761799.Fuster,A.,M.Plosser,P.Schnabel,and J.Vickery(2018).“The Role of Technology in Mortgage Lending.”Federal Reserve Bank of New York Staff Report 836(February).Gambacorta,L.,Y.Huang,H.Qiu,

285、and J.Wang(2019).“How Do Machine Learning and Non-traditional Data Affect Credit Scoring?New Evidence from a Chinese Fintech Firm.”BIS Working Paper 834.Gambacorta,L.,Y.Huang,Z.Li,H.Qiu,and S.Chen(2020).“Data vs Collateral.”BIS Working Paper 881(September).Goldstein,I.,J.Jagtiani,and A.Klein(2019).“

286、Fintech and the New Financial Landscape”BPI Banking Perspectives,Volume 7,Q1(March).Han,L.,S.Fraser,and D.J.Storey(2009).“Are Good or Bad Borrowers Discouraged from Applying for Loans?Evidence from US Small Business Credit Markets.”Journal of Banking and Finance 33(2),415424.Hau,H.,Y.Huang,H.Shan,an

287、d Z.Sheng(2018).“Fintech Credit,Financial Inclusion and Entrepreneurial Growth.”University of Geneva Working Paper.Hirt,M.,and P.Willmott(2014).“Strategic Principles for Competing in the Digital Age.”McKinsey Quarterly Review.Howell,S.T.,T.Kuchler,D.Snitkof,J.Stroebel,and J.Wong(2022).“Automation in

288、 Small Business Lending Can Reduce Racial Disparities:Evidence from the Paycheck Protection Program”NBER Working Paper 29364(February).Huang,Y.,C.Lin,Z.Sheng,and L.Wei(2018).“Fintech Credit and Service Quality.”Hong Kong Baptist University Working Paper.32 Hughes,J.,J.Jagtiani,and C.G.Moon(2022).“Co

289、nsumer Lending Efficiency:Commercial Banks Versus a fintech Lender,”Financial Innovation(forthcoming).Jagtiani,J.,L.Lambie-Hanson,and T.Lambie-Hanson(2021).“Fintech Lending and Mortgage Credit Access,”The Journal of Fintech 1:150.Jagtiani,J.,and C.Lemieux(2016).“Small Business Lending After the Fina

290、ncial Crisis:A New Competitive Landscape for Community Banks,”Economic Perspectives,Federal Reserve Bank of Chicago,3,Q3.Jagtiani,J.,and K.John(2018).“Fintech The Impact on Consumers and Regulatory Responses.”Journal of Economics and Business 100,November-December,16.Jagtiani,J.,and C.Lemieux(2018).

291、“Do Fintech Lenders Penetrate Areas That Are Underserved by Traditional Banks?”Journal of Economics and Business(June).Jagtiani,J.,T.Vermilyea,and L.Wall(2018).“The Roles of Big Data and Machine Learning in Bank Supervision.”The Clearing House:Banking Perspectives,Quarter 1.Jagtiani,J.,and C.Lemieux

292、(2019).“The Roles of Alternative Data and Machine Learning in fintech Lending:Evidence from the LendingClub Consumer Platform.”Financial Management,Winter 2019,48:4,10091029.Liu,H.,and D.Volker(2020).“Where Have the Paycheck Protection Loans Gone So Far?”FRBNY Liberty Street Economics(May 6).Lu,L.(2

293、018).“How a Little Ant Challenges Giant Banks?The Rise of Ant Financial(Alipay)s Fintech Empire and Relevant Regulatory Concerns.”International Company and Commercial Law Review 28,1230.Mach,T.,C.Carter,and C.R.Slattery(2014).“Peer-to-Peer Lending to Small Businesses,”SSRN Electronic Journal.Mijid,N

294、.,and A.Bernasek(2013).“Decomposing Racial and Ethnic Differences in Small Business Lending:Evidence of Discrimination.”Review of Social Economy 71(4),443473.Tang,H.(2019).“Peer-to-Peer Lenders versus Banks:Substitutes or Complements?”Review of Financial Studies 32(5),19001938.Ziegler,T.,R.Shneor,K.

295、Wenzlaff,B.Wang,J.Kim,A.Odorovic,F.Ferri de Camargo Paes,K.Suresh,B.Zhang,D.Johanson,C.Lopez,L.Mammadova,N.Adams,and D.Luo(2020).“The Global Alternative Finance Market Benchmarking Report.”(April,available at https:/www.jbs.cam.ac.uk/faculty-research/centres/alternative-finance/publications/the-glob

296、al-alternative-finance-market-benchmarking-report/).33 Appendix Distribution of Loan Maturity by FC Risk Bands Table A1 FC Risk Band A+A B C D Total Loan Maturity in Months 6 0.34%0.15%0.13%0.06%0.01%0.68%12 1.20%1.15%0.87%0.39%0.13%3.73%24 2.35%2.44%2.67%1.17%0.40%9.04%36 4.99%6.45%6.96%3.37%1.03%2

297、2.80%48 2.97%4.16%4.49%2.33%1.26%15.21%60+9.91%16.24%13.43%6.98%1.99%48.54%Total 21.76%30.59%28.54%14.30%4.82%100%Source:Funding Circle.Funding Circle SBL Pairwise Correlations Funding Circle SBL Loan Characteristics and Local Economic Factors Table A2 Loan amount Loan maturity in months Acquisition

298、 score Loan APR FICO at origination VantageScore 12-month del cy dummy1 24-month del cy dummy2 FC rating A+FC rating A FC rating B FC rating C FC rating D Origination year 2016 Origination year 2017 Origination year 2018 Origination year 2019 Ln(profit)Ln(gross revenue)Unemployment HPI Loan maturity

299、 in months 0.16 1 Acquisition score-0.06-0.01 1 Loan APR-0.14 0.02-0.02 1 FICO at origination 0.15-0.03 0.03-0.41 1 VantageScore 0.15-0.03 0.02-0.46 0.72 1 12-month delinquency dummy1 0.02 0.00-0.02 0.15-0.09-0.08 1 24-month delinquency dummy2 0.04 0.02-0.03 0.15-0.12-0.12 0.74 1 FC rating A+0.05-0.

300、07 0.02-0.58 0.32 0.35-0.07-0.08 1 FC rating A 0.08 0.05-0.01-0.36 0.10 0.11-0.06-0.06-0.35 1 FC rating B-0.03 0.00 0.00 0.23-0.14-0.16 0.01 0.02-0.33-0.42 1 FC rating C-0.07 0.02-0.01 0.48-0.21-0.23 0.08 0.08-0.22-0.27-0.26 1 FC rating D-0.10 0.00-0.01 0.63-0.19-0.21 0.11 0.12-0.12-0.15-0.14-0.09 1

301、 Origination year 2016 0.01-0.13-0.01-0.01-0.08-0.05 0.04 0.09-0.08 0.00 0.07 0.01-0.03 1 Origination year 2017 0.00-0.05 0.01-0.09-0.04-0.04 0.00 0.06 0.16-0.01-0.06-0.08-0.03-0.22 1 Origination year 2018 0.01 0.09-0.01 0.08-0.01-0.02 0.05 0.00-0.07 0.01-0.04 0.06 0.12-0.30-0.46 1 Origination year

302、2019-0.02 0.05 0.01 0.01 0.12 0.11-0.09-0.13-0.02 0.00 0.06 0.01-0.08-0.21-0.32-0.44 1 Ln(profit)0.34-0.05-0.03-0.08 0.04 0.06 0.00 0.00 0.05 0.03-0.03-0.04-0.05 0.04 0.02-0.03-0.02 1 Ln(gross revenue)0.60-0.09-0.10-0.15 0.15 0.14-0.01-0.01 0.09 0.06-0.05-0.08-0.08 0.09 0.02-0.06-0.02 0.40 1 Unemplo

303、yment-0.01 0.02 0.01 0.00-0.01 0.01 0.01 0.01 0.01-0.02 0.01 0.00 0.00 0.04 0.01 0.00-0.05-0.01 0.00 1 HPI 0.07-0.05 0.01-0.01 0.05 0.01 0.01 0.00-0.01 0.00 0.00 0.00 0.00 0.00-0.01 0.00 0.02 0.05 0.07-0.04 1 County business bankruptcy filings per capita 0.03-0.01 0.01-0.01 0.01 0.01 0.01-0.01-0.01

304、0.02 0.00-0.02 0.00 0.01 0.00-0.01 0.00 0.03 0.01-0.07 0.12 Bold figures indicate statistical significance at the 5 percent level.The sample includes loan-level data from Funding Circle SBL Platform for the period 20162019.1 Takes the value of 1 if loan becomes delinquent(60 days past due)as of 12 m

305、onths after origination and zero otherwise.2 Takes the value of 1 if loan becomes delinquent(60 days past due)as of 24 months after origination and zero otherwise.Sources:Funding Circle and Haver Analytics.35 LendingClub SBL APR by LendingClub Rating and FICO Scores in the U.S.Table A3 LendingClub R

306、isk Rating Total FICO Portfolio share D C B A A+FICO score Low risk 24.0%22.5%21.3%17.0%12.5%17.6%42.0%Medium risk 27.2%26.7%24.4%18.8%13.6%22.5%46.6%High risk 29.0%28.7%25.2%19.6%14.6%25.7%11.4%Total LC Risk Rating 27.2%26.2%23.8%18.2%13.0%21.4 Portfolio share 6.9%19.4%26.5%26.6%20.7%This table sho

307、ws APRs for different ranges of FICO score and LendingClub risk ratings,for loans that were originated on the LendingClub SBL platform during the period 20152019.The(discrete).LendingClub risk ratings at origination are mapped into five different risk groups(A+for categories R1R2 or C1C3,A for R3R4

308、or C4C7,B for R5R6 or C8C11,C for R7R8 or C12C15,and D for R9R10 or C16C20).The(continuous)scores of the FICO credit bureau are divided into three segments corresponding to risk level(low,for scores higher than 739;medium,for scores between 670 and 739;and high,for scores below 670).Source:Authors c

309、alculations based on data from LendingClub.Credit Access Estimations Table A4 Funding Circle SBL Lending Ratio1.(I)(II)(III)(IV)(V)County unemployment 0.00197*0.00199*0.00197*0.00197*(0.000421)(0.000422)(0.000421)(0.000421)County HPI(in 00s)0.000159 0.000178 0.000157 0.000144 (0.00132)(0.00132)(0.00

310、132)(0.00132)County business bankruptcy 48.21*47.95*48.24*48.19*filings per capita (7.098)(7.077)(7.097)(7.102)Median income(in 00,000s)0.0118*0.0118*0.0118*0.0118*(0.00131)(0.00131)(0.00131)(0.00131)SBL concentration(in 000s)0.00110 0.00114 0.00109 0.00109 based on non-CRA report (0.000839)(0.00083

311、9)(0.000839)(0.000839)Population(%)0.289*0.292*0.290*0.292*0.292*(0.0170)(0.0180)(0.0180)(0.0180)(0.0180)Dummy,decrease in branches 0.00210*(0.000963)Percentage decrease 0.00289 in branches (0.00465)Percent change in branches 0.00343 (0.00322)Observations 10,279 9,688 9,688 9,688 9,688 R2 0.074 0.08

312、5 0.085 0.085 0.085*/*/*denotes results that are significant at the 1%/5%/10%levels,respectively.The dependent variable is the ratio of SBL loans originated(by Funding Circle SBL platform)in zip code i in year t relative to total SBL loans(in all zip codes)originated in year t.The regressions includ

313、e a constant and state-level dummies.The sample is based on loan-level data from Funding Circle SBL platform for the period 2016:Q1 2019:Q2.Sources:Funding Circle,CRA data,FDIC Summary of Deposits,Call Reports,and Haver Analytics.36 Default Probability as of 12 months After Origination Table A5 Deli

314、nquent Loan Dummy 12 Months After Origination (I)(II)(III)Acquisition score-0.000012-0.000010*-0.000009*0.000008 0.000005 0.000005 FICO at origination-0.00603*-0.00342*(0.00149)(0.00151)VantageScore-0.00358*0.000815 (0.00125)(0.00131)FC rating A 0.580*0.533*(0.203)(0.206)FC rating B 1.210*1.128*(0.1

315、94)(0.207)FC rating C 1.886*1.781*(0.199)(0.217)FC rating D 2.583*2.451*(0.218)(0.241)Ln(profit)0.00561 0.0287 0.0240 (0.0407)(0.0424)(0.0424)Ln(gross revenue)-0.281*-0.271*-0.264*(0.0630)(0.0634)(0.0635)Ln(loan amount)0.454*0.502*0.519*(0.0903)(0.0942)(0.0949)Loan maturity in months-0.00339-0.00282

316、-0.00313 (0.00364)(0.00377)(0.00379)Unemployment 0.0742 0.0546 0.0529 (0.0461)(0.0472)(0.0471)County HPI 0.00247 0.00168 0.00178 (0.00151)(0.00153)(0.00153)County business bankruptcy -622.6 -555.4 -532.0 filings per capita (1,028)(1,023)(1,024)Observations 11,625 11,630 11,625 Pseudo R2 0.0808 0.121

317、 0.123*/*/*denotes results that are significant at the 1%/5%/10%levels,respectively.The table reports the estimates for a logit regression including a constant,state dummies,and origination-year dummies.The dependent variable takes the value of 1 if loan is the loan becomes delinquent(60+DPD)as of 1

318、2 months after origination and zero otherwise.The sample includes loan-level data from Funding Circle SBL Platform for the period 20162019.Sources:Funding Circle,CRA data,FDIC Summary of Deposits,Call Reports,and Haver Analytics 37 (a)ROC Curves Unemployment above the Median Table A6 Panel A:ROC Cur

319、ves 12-Month Delinquency Rates Observations AUROC Std.Err.95%Confidence Interval FICO Score 6,153 0.679 0.0162 0.64736 0.71073 VantageScore 6,153 0.6768 0.0165 0.64445 0.7092 FC Risk Grades 6,153 0.7536 0.0148 0.72457 0.78264 FC Risk Grades and APR Residuals 6,153 0.7605 0.0146 0.73193 0.78905 Panel

320、 B:ROC Curves 24-Month Delinquency Rates Observations AUROC Std.Err.95%Confidence Interval FICO Score 6,123 0.7003 0.0125 0.67572 0.72482 VantageScore 6,123 0.698 0.0126 0.67335 0.72274 FC Risk Grades 6,123 0.7477 0.0115 0.72514 0.77019 FC Risk Grades and APR Residuals 6,123 0.7533 0.0114 0.73091 0.

321、77564(b)ROC Curves Unemployment at or below the Median Panel A:ROC Curves 12-Month Delinquency Rates Observations AUROC Std.Err.95%Confidence Interval FICO Score 6,482 0.7567 0.0142 0.72886 0.78456 VantageScore 6,482 0.7493 0.0144 0.72117 0.77744 FC Risk Grades 6,482 0.7803 0.014 0.75293 0.8077 FC R

322、isk Grades and APR Residuals 6,482 0.7804 0.0139 0.75225 0.80678 Panel B:ROC Curves 24-Month Delinquency Rates Observations AUROC Std.Err.95%Confidence Interval FICO Score 6,386 0.7685 0.0115 0.74592 0.79105 VantageScore 6,386 0.7589 0.0116 0.7361 0.78168 FC Risk Grades 6,386 0.7896 0.011 0.76808 0.

323、81108 FC Risk Grades and APR Residuals 6,386 0.79 0.011 0.76851 0.81154 The table reports the estimates for the logit regression,which include state-and origination year-level dummies,as reported in Table 6.The sample includes only zip codes with an unemployment rate above the median in panel(a)and

324、below the median in panel(b).Source:Funding Circle.38 SBL Lending Activity by State In U.S.Dollars per capita Figure A1 Funding Circle(20162019)LendingClub(20152019)The graphs show the total amount lent in each state by each of the two fintech firms over the period indicated divided by the 2019 popu

325、lation in each State.Sources:Funding Circle,LendingClub,U.S.Census Bureau,authors calculations.LendingClub Credit Portfolio by County Figure A2 Average VantageScore by County1 Total Number of Loans per County2 1 Average VantageScore of LendingClub SBL Platforms small business borrowers in each count

326、y.2 Average number of SBL loans originated by LendingClub SBL Platform in each county.Sources:LendingClub,authors calculations.39 Correlation Between Funding Circles Risk Bands and Traditional Credit Scores(FICO and VantageScore)Correlation Coefficient Figure A3 Source:Funding Circle.Correlation Bet

327、ween LendingClub Rating Grades and FICO and VantageScore Figure A4 Source:LendingClub.40 Predictive Power of FICO,VantageScore,and Funding Circle Risk Grades Figure A5 ROC Curve 12-Month Delinquency Rates ROC Curve 24-Month Delinquency Rates Note:Based on estimates for a logit regression including s

328、tate-and origination year-level dummies.All credit scores are divided in 5 buckets.The FICO scores are divided into five buckets Poor(FICO800).The VantageScore is also divided into five buckets:Very Poor(scores 750).The x-axes show the fraction of false positives,whereas the y-axes show the fraction

329、 of true positives.The higher the curve the stronger the performance of the model.Sources:Funding Circle;What Is a Good Credit Score?Forbes Advisor.Funding Circle Risk Bands Are Functionally Similar to Other Risk Scores Figure A6 APR Is Closely Linked with Risk Band Risk Bands Map to FICO Score.and

330、to VantageScore Per cent Score Score Source:Funding Circle.Previous volumes in this series 1040 September 2022 Quantifying the role of interest rates,the Dollar and Covid in oil prices Emanuel Kohlscheen 1039 September 2022 Cyber risk in central banking Sebastian Doerr,Leonardo Gambacorta,Thomas Lea

331、ch,Bertrand Legros and David Whyte 1038 September 2022 Building portfolios of sovereign securities with decreasing carbon footprints Gong Cheng,Eric Jondeau and Benit Mojon 1037 August 2022 Big Techs vs Banks Leonardo Gambacorta,Fahad Khalil and Bruno M Parigi 1036 August 2022 The scarring effects o

332、f deep contractions David Aikman,Mathias Drehmann,Mikael Juselius and Xiaochuan Xing 1035 July 2022 Cross-border financial centres Pamela Pogliani and Philip Wooldridge 1034 July 2022 Debt sustainability and monetary policy:the case of ECB asset purchases Enrique Alberola,Gong Cheng,Andrea Consiglio

333、 and Stavros A Zenios 1033 July 2022 The Holt-Winters filter and the one-sided HP filter:A close correspondence Rodrigo Alfaro and Mathias Drehmann 1032 July 2022 Capital flows and monetary policy trade-offs in emerging market economies Paolo Cavallino and Boris Hofmann 1031 July 2022 Risk capacity,portfolio choice and exchange rates Boris Hofmann,Ilhyock Shim and Hyun Song Shin 1030 July 2022 Mis