Equity in STEM Pathways: Machine Learning for Predicting Underrepresented Students' STEM Major Choices

• In Event: AERA Roundtable Session Friday 1:30 pm Four Seasons Ballroom 4
  In Roundtable Session: Exploring Assessment Data for Psychological Insights and Technological Advances in Education (Table 5)

Abstract

The underrepresentation of certain demographic groups in STEM fields remains a critical issue. This study uses data from the High School Longitudinal Study of 2009 (HSLS:09) to identify factors influencing underrepresented high school students' decisions to pursue STEM majors. Employing the Classification and Regression Tree algorithm, the study analyzes 11,560 students, considering 107 variables related to demographics, family background, motivation, and school context. Key findings reveal gender and race-specific influences on STEM preferences, with test math scores, parental involvement, and self-efficacy being significant predictors. These insights provide a foundation for developing targeted interventions to enhance diversity and inclusivity in STEM education and careers.

Authors

• Gozde Sirganci, Southern Methodist University

• Yanjun Pan, Southern Methodist University

• Can Mese, Indiana University