NBER WP 29840 (Di Maggio, Ratnadiwakara, Carmichael, 2022) — "Invisible Primes: Fintech Lending with Alternative Data"
Summary
Claim. Fintech lenders using alternative data identify "invisible primes" — borrowers whose true creditworthiness is unobservable to traditional bureau-only scoring — and lend to them profitably. Explicit information-asymmetry-reduction framing.
Source. Marco Di Maggio, Dimuthu Ratnadiwakara, Don Carmichael, "Invisible Primes: Fintech Lending with Alternative Data," NBER Working Paper 29840 (2022). Primary academic.
Confidence. Verified. NBER working paper; primary academic source on the alt-data credit thesis.
Caveats. US fintech context (LendingClub-era lenders); generalising the exact lift to Canadian SMBs is inferential. The mechanism is general, the magnitudes are setting-specific.
Implication / use. Cleanest peer-reviewed grounding for risk-domain decision edge. Use to connect Akerlof (Akerlof 1970 — "The Market for Lemons"; asymmetric information can collapse markets (Nobel 2001)) to a measured commercial outcome in a familiar setting.
Related entries
Referenced by (4)
- rule Rule: prefer peer-reviewed / award-vetted magnitudes (Edelman, NBER, INFORMS) over vendor-recycled figures depends-on
- reference IFC / World Bank — "Cracking the Credit Code: Alternative Data and AI for Financial Inclusion" (2026) relates-to
- reference J-PAL Agarwal et al. 2019 India — mobile / social-footprint ML predicts loan defaults more effectively than credit-only models relates-to
- reference PMC peer-reviewed — excluding alternative data led to "a significant decline in model performance" (PMC11108212) relates-to