Fintech for the Poor: Financial Intermediation Without Discrimination
Open accessAbstract
I ask whether machine learning (ML) algorithms improve the efficiency in lending without compromising on equity in a credit environment where soft information dominates. I obtain loan application-level data from an Indian bank. To overcome the problem of the selective labels, I exploit the incentive-driven within officer difference in leniency within a calendar month. I find that the ML algorithm can lend 60% more at loan officers’ delinquency rate or achieve a 33% lower delinquency rate at loan officers’ approval rate. The efficiency is maintained even when the algorithm is explicitly prevented from discriminating against disadvantaged social classes.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Digital financial inclusion reduces potential credit discrimination against low-income groups and improves risk control ability of the finance industry.
“it identifies customer information through big data, reduces the potential credit discrimination of traditional financial institutions against low-income groups, and improves the risk control ability of the finance industry [9].”
From Digital financial inclusion and quality of economic growth (2023) · cites this paper as [9]
Cites
Financial intermediation and delegated monitoring
Diamond, D. W. (1984) · The Review of Economic Studies · doi:10.2307/2297430 · Cited by 8,476 · cited 2× · see citing works
“The algorithm only assists in screening and not monitoring (Diamond (1984)).”
Artificial Intelligence: The Ambiguous Labor Market Impact of Automating Prediction
Agrawal, A., Gans, J. S., & Goldfarb, A. (2019) · Journal of Economic Perspectives · doi:10.1257/jep.33.2.31 · Cited by 685 · see citing works
Kleinberg, J., Ludwig, J., Mullainathan, S., & Obermeyer, Z. (2015) · American Economic Review · doi:10.1257/aer.p20151023 · Cited by 584 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Digital financial inclusion and quality of economic growth
Xi, W., & Wang, Y. (2023) · Heliyon · doi:10.1016/j.heliyon.2023.e19731 · Cited by 76 · see citing works
“On the other hand, it identifies customer information through big data, reduces the potential credit discrimination of traditional financial institutions against low-income groups, and improves the risk control ability of the finance industry [9].”
Algorithmic monoculture and social welfare
(2023) · The Societal Impacts of Algorithmic Decision-Making · doi:10.1145/3603195.3603202
- Authors
- Tantri, P.
- Affiliations
- Indian School of Business (IN)
- Corresponding author
- Tantri, Prasanna
- ORCID
- Tantri, Prasanna
- Venue
- Review of Finance
- Publisher
- Oxford University Press (OUP)
- Published
- 2020-09-12
- Volume
- 25
- Issue
- 2
- Pages
- 561-593
- ISSN
- 1382-6662 (ISSN-L)
- 1572-3097
- 1573-692X
- OpenAlex
- W3111861264
- Cited by
- 94
- References
- 3
- Citations by year
- 2026: 8 · 2025: 15 · 2024: 18 · 2023: 35 · 2022: 9 · 2021: 6 · 2020: 2 · 2019: 1
- FWCI
- 14.77
- Type
- journal article
- Language
- en
- Open access
- green
- doi.org
- Licence
- academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model (vor)
- Locations
- European Finance Review (publishedVersion)
- SSRN Electronic Journal (acceptedVersion)
- Digital Eprints Services at ISB (DESI) (Indian School of Business) (submittedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- Topics
- Social Sciences › Business, Management and Accounting › Management Information Systems › FinTech, Crowdfunding, Digital Finance
- Social Sciences › Business, Management and Accounting › Accounting › Financial Distress and Bankruptcy Prediction
- Social Sciences › Economics, Econometrics and Finance › Economics and Econometrics › Microfinance and Financial Inclusion
- Keywords
- fintech, credit discrimination, soft information, loan delinquency, lending, loan officers, algorithmic fairness, financial intermediation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
