Using Grocery Data for Credit Decisions
64 Pages Posted: 8 Jul 2021 Last revised: 12 Mar 2024
Date Written: March 10, 2024
Abstract
Many consumers across the world struggle to gain access to credit due to the lack of credit scores. This paper explores the potential of a new type of alternative data source, namely grocery transaction data, to assess consumers’ creditworthiness. Our analysis takes advantage of a unique, individual-level match of credit card data and supermarket loyalty card data, which enables us to build a credit scoring algorithm that incorporates grocery data. We show that incorporating signals derived from grocery data improves the accuracy of credit risk prediction, above and beyond traditional data sources such as income and credit scores. Through simulations of different credit extension decision rules, we illustrate that the distributional impact of using grocery data relies heavily on how lenders utilize the predictions, with contrasting effects on the likelihood of credit approval for lower-income consumers. Together, our findings highlight that grocery data can serve as a channel through which traditionally underserved consumer groups in credit markets can signal their creditworthiness to lenders, provided that lenders harness the data appropriately.
Keywords: Grocery data, Alternative data, Financial inclusion, Consumer finance, Credit cards market, Habits, Economics of data
JEL Classification: D12, D18, G40, G51
Suggested Citation: Suggested Citation