Working Paper: NBER ID: w29840
Authors: Marco Di Maggio; Dimuthu Ratnadiwakara; Don Carmichael
Abstract: We exploit anonymized administrative data provided by a major fintech platform to investigate whether using alternative data to assess borrowers' creditworthiness results in broader credit access. Comparing actual outcomes of the fintech platform’s model to counterfactual outcomes based on a “traditional model” used for regulatory reporting purposes, we find that the latter would result in a 70% higher probability of being rejected and higher interest rates for those approved. The borrowers most positively affected are the “invisible primes”--borrowers with low credit scores and short credit histories, but also a low propensity to default. We show that funding loans to these borrowers leads to better economic outcomes for the borrowers and higher returns for the fintech platform.
Keywords: Fintech; Lending; Alternative Data; Credit Access
JEL Codes: G23; G5; G51
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| credit scores below 680 (G51) | rejection by traditional lending models (G21) |
| low credit score borrowers (G51) | improved economic outcomes (O49) |
| alternative data for creditworthiness assessments (G51) | broader credit access (G21) |
| Upstart's underwriting model (G22) | higher returns for the platform (D26) |
| borrowers funded by Upstart (G51) | improvements in credit scores (G51) |
| borrowers funded by Upstart (G51) | increased likelihood of home purchasing (R21) |