In previous research and development, the developer created a website, Nimble, for K12 administrators to manage the process of recruiting, interviewing, and hiring educators. In this Phase I project, the research team will develop a new prototype with a machine learning engine that predicts the strongest candidates for specific schools to interview, and a user-friendly dashboard for administrators to manage all aspects of the application and hiring process.  At the end of Phase I, a pilot study with 20 school principals, half who use the prototype and half that do not, participants will be tasked to select the 30 best candidates to interview out of a group of 100 candidates. The researchers will examine whether the machine learning engine produces useful results and whether these results would show promise for improving decisions compared to principals who use business as usual procedures for selecting what candidates to interview and hire.

Related IES Projects: Research Partnership to Improve Human Resource Management in Minneapolis Public Schools (R305H160036); Applicants at the Doorstep: Improving Hiring Practices through a Better Understanding of the Link Between Applicant Information and Teacher Quality (91990021C0020).