This Project Grant from the National Science Foundation's Division of Research on Learning in Formal and Informal Settings will support the development of personalized math course-taking plans for high school students using dynamic treatment regimes. With $349,995 in funding over a three-year period from January 2023 to December 2025, the grantee, Teachers College Columbia University, will utilize machine learning and large-scale educational data to tailor math course recommendations to individual students. Incorporating algorithmic fairness constraints, the project aims to reduce existing disparities in course-taking patterns among different racial, ethnic and income groups. By integrating optimal policy learning methods with considerations for equitable access, this work under the NSF's STEM Education program (CFDA 47.076) seeks to transform how K-12 students take math and STEM courses to expand opportunities for all learners.