Buying and Payment Habits: Using Grocery Data to Predict Credit Card Payments
This study shows that individuals’ habits in grocery shopping are incrementally useful in predicting their credit card payment behaviors, and that such incremental predictive power can alter firm decisions in the consumer lending market. Guided by different theories of habits, the authors find five broad grocery shopping habits that are correlated with credit card payment behaviors: (1) shopping the same day of week, (2) spending similar amounts on each trip, (3) consistently buying the same brands and categories, (4) taking advantage of deals and promotions, and (5) buying healthier products. Using machine learning models, the authors show that the incremental predictive gain in AUC from knowledge of the grocery habits ranges from 0.5% to 9.8%, which varies with the baseline data of lenders. Simulations of credit card issuers’ credit extension decisions suggest that the profit impact of such pre- dictive gain is greatest for consumers who do not have an established credit history. Further, use of grocery data may disproportionately increase the likelihood of getting access to credit for lower-income consumers. Overall, our results suggest that habits persist across domains, which opens up new opportunities in consumer lending.
Eric T. Anderson, Joonhyuk Yang, Jung Youn Lee
Anderson, Eric T., Joonhyuk Yang, and Jung Youn Lee. 2023. Buying and Payment Habits: Using Grocery Data to Predict Credit Card Payments.