Title

Measuring Bias in Consumer Lending

Author(s)

Will Dobbie Will Dobbie (Princeton University and NBER)

Andres Liberman Andres Liberman (New York University)

Daniel Paravisini Daniel Paravisini (London School of Economics and CEPR)

Vikram Pathania Vikram Pathania (University of Sussex)

Abstract

This paper tests for bias in consumer lending decisions using administrative data from a high-cost lender in the United Kingdom. We motivate our analysis using a simple model of bias in lending, which predicts that profits should be identical for loan applicants from different groups at the margin if loan examiners are unbiased. We identify the profitability of marginal loan applicants by exploiting variation from the quasi-random assignment of loan examiners. We find significant bias against both immigrant and older loan applicants when using the firm’s preferred measure of long-run profits. In contrast, there is no evidence of bias when using a short-run measure used to evaluate examiner performance, suggesting that the bias in our setting is due to the misalignment of firm and examiner incentives. We conclude by showing that a decision rule based on machine learning predictions of long-run profitability can simultaneously increase profits and eliminate bias.

Creation Date

2018-08

Section URL ID

IRS

Paper Number

623

URL

https://dataspace.princeton.edu/bitstream/88435/dsp01tb09j8412/3/623.pdf

File Function

Jel

G41; J15; J16

Keyword(s)

Discrimination; Consumer Credit

Suppress

false

Series

1