The adoption of Artificial Intelligence (AI) for hiring processes is often impeded by a scarcity of comprehensive employee data. We hypothesize that the inclusion of behavioral measures elicited from applicants can enhance the predictive accuracy of AI in hiring. We study this hypothesis in the context of microfinance credit officers. We focus on cognitive and behavioral measures commonly used in economics and psychology.

Access to elite colleges varies drastically based on gender and socioeconomic status (SES). In the U.S., children from top 1% income families are 77 times more likely to attend an elite institution than those from the bottom 20% income bracket [Chetty et al. 2017]. At the same time, females disproportionately enter less selective colleges and lower-paying jobs than men [Blau and Kahn 2017]. We investigate "misconfidence" --- the difference between student perception of their rank in the grade distribution and their real rank in the distribution. It is very common for individuals to have biased beliefs about their own abilities [Möbius et al. 2022]. While several studies show a correlation between confidence and educational choices, there is a lack of causal evidence on the impact of misconfidence on college choices.