Background: Predicting student performance in online learning is difficult due to class imbalance and limited model interpretability. At-risk students are fewer than high performers, biasing predictions, and methods like SMOTE fail to preserve temporal patterns. Although black-box models are...

We study how AI tutoring affects learning in higher education through a randomized experiment with 334 university students preparing for an incentivized exam. Students either received only textbook material, restricted access to an AI tutor requiring initial independent reading, or unrestricted...

We demonstrate that racial biases against tutors hinder learning. In e-learning experiments, U.S. conservatives are more likely to disregard advice from Black tutors, resulting in reduced performance compared to learners taught by white tutors. We show that the bias is unconscious and,...

Purpose - This study examines the behavioral and contextual determinants influencing digital payment trust and perceived cybersecurity (DPTS) in India, focusing on the roles of ease of use, perceived benefits, social influence and grievance redressal mechanisms. It further explores how DPTS,...

Although Asian economies have increased access to education, students' learning often trails grade level expectations. In the Philippines, learning worsened through prolonged classroom closure during the coronavirus disease (COVID-19) pandemic. Together with the Department of Education, we...

We study how AI tutoring affects learning in higher education through a randomized experiment with 334 university students preparing for an incentivized exam. Students either received only textbook material, restricted access to an AI tutor requiring initial independent reading, or unrestricted...