Using AI and Behavioral Finance to Cope with Limited Attention and Reduce Overdraft Fees

Abstract

In a randomized field experiment using a large personal financial management platform operating in the United States and Canada, we investigate mechanisms to reduce overdraft fees. A sample of users identified via an artificial intelligence (AI) algorithm as having a propensity to overdraw their accounts were sent recurring, as needed, reminder notices to test the efficacy of different framings in reducing the number of overdraft fees. Employing parametric identifications, as well as time-to-event semi-parametric analysis, we learn that sending as needed reminders proved effective in and of itself, and the impact was significantly enhanced by simplifying the message. A negative framing of the simplified version elicited greater engagement and had a stronger impact than a positive framing. Significant effects are seen predominantly among users with medium to high annual incomes. We relate our findings to the literature on limited attention and the ostrich phenomenon. Our work also contributes to the literatures on financial technology, AI, and human-computer interaction.

Keywords: artificial intelligence, behavioral finance, overdraft, limited attention, ostrich