Applying Machine Learning to Predict Mathematics Literacy of Resilient Students From High-Performing Economies: Does Culture Matter?

• In Event: AERA Roundtable Session Friday 8:00 am Four Seasons Ballroom 2-3
  In Roundtable Session: Studies of Formative Assessment, Mathematics Literacy, and Play With Mathematics Tasks (Table 4)

Abstract

Mathematics is a crucial yet challenging subject for all students. Therefore, it is important to understand the role of academic resilience in mathematics, which enables students to overcome academic challenges. This study applied two machine learning algorithms, Lasso Regression (LR) and Random Forest (RF), to predict the mathematics literacy of resilient students from high-performing economies across cultures in PISA 2022. The findings indicated that LR outperformed RF in Western cultures, whereas RF outperformed LR in Eastern cultures. Furthermore, self-efficacy towards mathematics was the top predictor of mathematics literacy in Western cultures, whereas anxiety towards mathematics was the top predictor in Eastern cultures. This study provides guidance for developing the mathematics literacy of resilient students.

Authors

• Yimei Zhang, McGill University

• Maria Cutumisu, McGill University